Search

• Automatic handwritten analysis system has been developed to detect the gender of the writer. • Machine learning methods have been used to extract set of gender-related features. • Large Arabic dataset was collected to conduct the experiment of the gender detection system. • Novel set of features were chosen with the consultation of a graphologist and psychologist. • Benchmark dataset was used to compare the proposed detection system with another researcher works. Gender detection from handwritten documents is a crucial research area in many disciplines such as psychology, pyelography, graphology, and forensic analysis. Furthermore, this task is challenging due to the high similarity and overlap between individuals' handwriting. The performance of the document recognition and analysis systems, depends on the extracted features from handwritten documents, which can be a challenging task as this depends on extracting the most relevant information from row text. In this paper, a set of gender-related features suggested by a graphologist, to detect the gender of the writers, have been proposed. These features include margins, space between words, pen-pressure and handwriting irregularity. Both SVM and ANN classifiers have been used to train, validate and test the proposed approach on two different data sets: our data set FSHS and ICDAR2013 dataset. The proposed method has achieved high classification rates of 94.7% and 97.1% using SVM and ANN respectively. Meanwhile, our method outperformed state-of-arts methods when applied to the ICDAR2013 dataset with classification rates of 91.4% and 92.5% using SVM and ANN respectively. [ABSTRACT FROM AUTHOR]

• We investigate driving forces of different land-use types to BSD. • Diversified machine learnings are proposed for spatial interpolation fusion. • Hotspot detection establishes sampling points for reducing the MAUP effect. • Fusion models improve the interpolation performance: accuracy and stability. • Word clouds identifies predominant facility names in each land-use type. Land use plays a crucial role in promoting the bike-sharing demand. Traditionally, studies on bike-sharing demand (BSD) are mainly focused on its prediction through regression methods, but the influence of MAUP (modifiable areal unit problem) in modeling is ignored. This paper aims to model spatial BSD distribution and prove the driving forces of different land use types to BSD through a machine-learning-based multiple interpolation fusion method. The hotspot detection model is employed to establish sample points covering different land use types in urban areas. In order to capture the differences in adaptations among different urban regions and for different data sizes, six machine learning methods are applied and evaluated to improve BSD estimation by fusing five spatial interpolation algorithms, including Inverse Distance Weight, Spline, Kriging, Natural Neighborhood and Trend. The methodological verification of Beijing City shows that the fusion models improve the estimation performance compared with individual interpolation algorithms, and that GRNN (generalized regression neural network) method is superior to all the others. According to fitting results of all POIs based on the GRNN fusion model, we identify which types of facilities correspond to customers that will have a stronger preference for bike-sharing and demonstrate which facility names are more prominent in each land use type. The conclusions presented here enrich our understanding relationships between land-use and BSD, which provide a valuable foundation for the bike-sharing development. Compared with implementing regression in an analysis zone or a square grid, troubles caused by the MAUP are effectively solved through this method. [ABSTRACT FROM AUTHOR]

Real-time algorithms have to adapt and adjust to new incoming patterns to provide timely and accurate responses. This paper presents a new distributed forecasting algorithm for streaming time series called StreamWNN. StreamWNN starts with an offline stage in which a forecasting model based on tuples of information fusion is created with historical data. In particular, this model consists of the fusion of patterns composed of past values of the time series with the future values of their k-nearest neighbors. Afterwards, streaming data starts to arrive. The model is incrementally updated in the online stage using a buffer with streaming data that more accurately matches the current model patterns. The model can be updated daily, monthly, quarterly or based on error thresholds. The methodology has been applied to Spanish electricity demand time series providing more accurate results when the model is updated incrementally. The best error results are obtained with the daily update of the model, resulting in an error between 2% and 3.5% depending on the prediction horizon. The model provides better error results than other algorithms. • StreamWNN is a real-time forecasting algorithm for time series received in streaming. • The prediction model is based on the fusion of relevant information related to the nearest neighbors. • Incremental learning deals with the change of distribution of streaming data. • StreamWNN predicts accurately Spanish electricity consumption in real-time. [ABSTRACT FROM AUTHOR]

• Using multiple sensors to enable SUR to obtain high-precision estimated data. • Building MSIF model with multisource factors to enhance SUR's practicality in tasks. • Considering multi-sensor information to offset position, velocity and tracking error. • Combining with BPNN to improve the MSIF's effectiveness, accuracy, and feasibility. Currently, most of the existing fusion methods ignore the rich multi-source information of different types of sensor nodes in the underwater unknown environment, which makes it challenging for Autonomous Underwater Vehicles (AUVs) to accurately perceive the external environment and make actionable decisions. Considering the key issues such as attitude estimation, positioning and obstacle avoidance involved in performing AUV tasks, this paper proposed a Multi-Source Information Fusion (MSIF) model for Spherical Underwater Robots (SURs) we developed based on various low-cost sensors. Multi-source information from an Inertial Measurement Unit (IMU), Pressure Sensor Array (PSA), Obstacle Avoidance Sensor Array (OASA), Depth Sensor (DS), Looking-Down Camera (LDC) and Acoustic Communication System (ACS) were fused to enable SUR to obtain high-precision estimated data for attitude estimation, positioning and obstacle avoidance, etc. More precisely, according to the correlation between the sensors, the optimized model was constructed to compensate for angle errors, velocity errors, orientation errors, etc. Subsequently, a machine learning method using Back Propagation Neural Network (BPNN) was proposed to improve the accuracy and effectiveness of the MSIF model through feature selection, data training, and feature estimation, etc. Finally, a series of experiments were performed under different scenarios, such as motion and obstacle avoidance experiments. The theoretical derivation and comprehensive evaluations demonstrated the effectiveness and feasibility of the proposed model, which provided a new reference value for solving issues such as attitude estimation, positioning and obstacle avoidance of AUVs. [ABSTRACT FROM AUTHOR]

In practical applications, multi-view data depicting objects from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node relationships and graph information simultaneously via graph convolutional network that has drawn the attention from considerable researchers in recent years. Most of existing methods only consider the weighted sum of adjacency matrices, yet a joint neural network of both feature and graph fusion is still under-explored. To cope with these issues, this paper proposes a joint deep learning framework called Learnable Graph Convolutional Network and Feature Fusion (LGCN-FF), consisting of two modules: feature fusion network and learnable graph convolutional network. The former aims to learn an underlying feature representation from heterogeneous views, while the latter explores a more discriminative graph fusion via learnable weights and a parametric activation function dubbed Differentiable Shrinkage Activation (DSA) function. The proposed LGCN-FF is validated to be superior to various state-of-the-art methods in multi-view semi-supervised classification. [Display omitted] • Propose a joint deep learning framework for multi-view information fusion. • Conduct feature and graph fusion simultaneously under the same framework. • Develop a multi-stage training strategy to optimize different subproblems with back propagation. • Construct a learnable GCN framework with adaptive weights and a parametric differentiable shrinkage activation function. [ABSTRACT FROM AUTHOR]

Sleep posture is linked to several health conditions such as nocturnal cramps and more serious musculoskeletal issues. However, in-clinic sleep assessments are often limited to vital signs (e.g. brain waves). Wearable sensors with embedded inertial measurement units have been used for sleep posture classification; nonetheless, previous works consider only few (commonly four) postures, which are inadequate for advanced clinical assessments. Moreover, posture learning algorithms typically require longitudinal data collection to function reliably, and often operate on raw inertial sensor readings unfamiliar to clinicians. This paper proposes a new framework for sleep posture classification based on a minimal set of joint angle measurements. The proposed framework is validated on a rich set of twelve postures in two experimental pipelines: computer animation to obtain synthetic postural data, and human participant pilot study using custom-made miniature wearable sensors. Through fusing raw geo-inertial sensor measurements to compute a filtered estimate of relative segment orientations across the wrist and ankle joints, the body posture was characterised in a way comprehensible to medical experts. The proposed sleep posture learning framework offers plug-and-play posture classification by capitalising on a novel kinematic data augmentation method that requires only one training example per posture. Additionally, a new metric together with data visualisations were employed to extract meaningful insights from the postures dataset, demonstrate the added value of the data augmentation method, and explain the classification performance. The proposed framework attained promising overall accuracy as high as 100% on synthetic data and 92.7% on real data, on par with state of the art data-hungry algorithms available in the literature. • Used computer graphics tools to simulate a virtual sleep experiment. • Classification of sleep postures both through in silico and in vivo experiments. • Learning of twelve human sleep postures with one observation per posture. • Inertial sensor fusion enabled posture classification using quadruple joint angles. • Metrics and visualisations enabled quantitative and qualitative posture analysis. [ABSTRACT FROM AUTHOR]

Machine learning algorithms especially deep neural networks have seen tremendous growth in their real-world deployment. While these algorithms have to yield high performances for the task at hand, it is of equal importance that they are robust against the different kinds of singularities or adversarial anomalies. Researchers have generally addressed singularity detection independently for each anomaly, however, for the algorithms to be effective in the real world, the singularity detection algorithm must be able to handle a wide variety of attacks whether trained individually on them or not seen at the time of training. With this objective, in this paper, we propose a unique end-to-end transformation domain network to detect a variety of well-known attacks. The proposed architecture utilizes a combination of two different wavelet transformations to simultaneously learn low-level and high-level image features in a deep stacked layer fashion. The proposed method is generalized to handle a broad set of singularities of several computer vision algorithms whether operating in the object recognition domain or biometrics recognition. We showcase the results on a wide range of singularity points including (i) adversarial perturbations which are learned using deep learning networks, (ii) physical presentation attacks on face recognition which aim to produce fake data for the sensor for acquisition, and identification, (iii) synthetic images, and (iv) digital retouching of the images. Even with a zero-day or open-world attack setting, the results of the proposed algorithm show improvement over state-of-the-art results. The proposed architecture is agnostic to parameters, computationally efficient to provide a sustainable detector to resource-constrained institutions, provides robustness to attacks, and supports green computing. • A novel parameter-agnostic architecture is proposed to defend anomalies. • The proposed algorithm can handle adversaries in seen, unseen, and open-set settings. • The proposed algorithm is domain agnostic i.e., can handle vision and face datasets. • Our unified algorithm surpasses the SOTA works developed to handle specific attacks. • Bring a computationally feasible algorithm, it can be deployed on mobile devices. [ABSTRACT FROM AUTHOR]

A new adsorbent was prepared from municipal wastes (a mixture of Corn Stover, Paper Waste, and Yard Waste) by cationization with 3 ̶ Chloro ̶ 2 ̶ Hydroxypropyl Trimethylammonium Chloride. The FTIR spectrum confirmed the quaternary ammonium group's presence on the adsorbent surface (1450 cm−1). The maximum adsorption capacity (148 mg/g) was higher than the earlier reported values. Liu isotherm described well the adsorption process, with a high R2 adj value (0.997). The pseudo-first-order equation fits well for kinetic data, and thermodynamic experiments demonstrated the endothermic nature of the adsorption. The deep neural network (DNN) is applied to simulate the adsorption process, which outperformed the classical machine learning and shallow neural network models. The DNN model predicted accurately the adsorption process with the lowest deviation from the actual values with Mean Absolute Error (MAE = 3.2), Root Mean Squared Error (RMSE = 4.89), and the highest performance accuracy of R2 (0.96) as compared to various classical ML algorithms such as Linear Regressions (MAE = 12.53, RMSE = 18.01, R2 = 0.42), Random Forest (MAE = 5.81, RMSE = 10.05, R2 = 0.82), and Extra Trees (MAE = 4.35, RMSE = 8.22, R2 = 0.88). The utilized DNN model can be used for predicting the removal efficiency of dyes for various combinations of input parameters without going through laboratory experiments. ga1 • Matrix of municipal waste was converted into an absorbent by surface cationization. • The adsorbent had higher adsorption capacity for anionic dye Indigo Carmine. • Liu isotherm described well the adsorption process. • Classical machine learning models didn't predict accurately. • Deep Neural Network was able to model the adsorption process with 96% accuracy. [ABSTRACT FROM AUTHOR]

• FDD methods and process discussed in detail. • IoT and cloud technology for FDD is discussed. • Presents the detailed discussion on fault modeling. • Challenges and future prospects of FDD systems are discussed. This review study examines the latest research and developments in the fault detection and diagnostics of Heating Ventilation and Air Conditioning (HVAC) systems. This review describes the basics of Fault detection and diagnostics in the HVAC systems, and the methods developed for the FDD have been discussed in detail. Machine learning methods have become prevalent in the FDD. Supervised and unsupervised machine learning methods have been discussed. Data preprocessing and feature selection are the two essential steps of the FDD process using machine learning. Fault prognosis has also been discussed in brief. Further, fault modeling and its applications in the FDD have been covered. Various approaches have been used to model the different faults in HVAC systems. This paper reviews FDD systems based on four aspects, i.e., detection, diagnostics, prognostics, and modeling of faults. Then this review provides a comparative study of different FDD methods. Finally, the paper discusses future challenges for the more efficient FDD systems to reduce the energy consumption of the HVAC systems. [ABSTRACT FROM AUTHOR]

• An audio dataset with FSL and OSR considerations is proposed. • It contains real recordings from 34 classes of alarms and common domestic sounds. • Recordings were captured in real environments using the same device. • This dataset will avoid manipulations on existing datasets (common practice today). • Two baselines are proposed based on a transfer learning approach as starting points. The problem of training with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, using a limited number of samples. These sounds typically occur in domestic environments where many events corresponding to a wide variety of sound classes take place. Therefore, the detection of such alarms in a practical scenario can be considered an open-set recognition (OSR) problem. To address the lack of a dedicated public dataset for audio FSL, researchers usually make modifications on other available datasets. This paper is aimed at providing the audio recognition community with a carefully annotated dataset 1 for FSL in an OSR context comprised of 1360 clips from 34 classes divided into pattern sounds and unwanted sounds. To facilitate and promote research on this area, results with state-of-the-art baseline systems based on transfer learning are also presented. [ABSTRACT FROM AUTHOR]

Interpretability in intelligent models becomes a challenge in academic research and approaches that facilitate understanding the responses obtained in models based on artificial intelligence and machine learning. This paper presents a new logical fuzzy neuron based on the concept of null-uninorm, thus called null-unineuron to compose the architecture of an evolving neuro-fuzzy model. This new structural neuron can extract advanced fuzzy rules allowing AND and OR-connections of antecedents to better interpret and understand the analyzed problem. This three-layer model uses an evolving weighted fuzzification approach based on incremental data partitioning concepts for knowledge extraction through null-unineurons whose training procedure suits the classification of binary and multiclass patterns in an online and incremental way. The weights integrated in the evolving data partitioning algorithm belong to feature importance levels and achieve an automatic shrinkage of distance calculations along unimportant input directions (features), which in turn accounts for a soft dimension reduction and the likelihood to decrease over-fitting. The new architecture proposed in this model was, subject to pattern classification tests, being more efficient compared to related (evolving) neuro-fuzzy models in the literature. Finally, experiments on various real-world data sets proved that the evolving neuro-fuzzy model proposed in this paper can act in a simplified way in the extraction of knowledge from data while providing answers with a high degree of accuracy for pattern classification problems. [ABSTRACT FROM AUTHOR]

In this paper, we tackle a new learning paradigm called learning from complementary labels, where the training data specifies classes that instances do not belong to, instead of the accuracy labels. In general, it is more efficient to collect the complementary labels compared with collecting the supervised ones, with no need for selecting the correct one from a number of candidates. While current state-of-the-art methods design various loss functions to train competitive models by the limited supervised information, they overlook learning from the data and model themselves, which always contain fruitful information that can improve the performance of complementary label learning. In this paper, we propose a novel learning framework, which seamlessly integrates self-supervised and self-distillation to complementary learning. Based on the general complementary learning framework, we employ an entropy regularization term to guarantee the network outputs exhibit a sharper state. Then, to intensively learn information from the data, we leverage the self-supervised learning based on rotation and transformation operations as a plug-in auxiliary task to learn better transferable representations. Finally, knowledge distillation is introduced to further extract the "dark knowledge" from a network to guide the training of a student network. In the extensive experiments, our method surprisingly demonstrates compelling performance in accuracy over several state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Testing of Integrated Circuits (ICs) is essential for weeding out defects before the products are shipped to customers. With the growing complexity of ICs, high-cost specification tests are becoming a bottleneck owing to their lengthy Test Time (TT). TT becomes particularly critical when the overall costs of ICs have to be taken into consideration. Considering the problem that TT takes too long in the traditional test, i. e. , a test with full Test Patterns (TPs), this paper proposes an improved K-Nearest Neighbor (KNN) algorithm to classify the defects, i. e. , this TP selection approach utilizes a classification model to select the valid patterns only, to shorten the TT. Experimental results demonstrate that compared with the traditional method, the proposed method successfully reduces the TT by 1.75 times. Furthermore, the experimental results represent the optimal compromise between TC and Test Quality (TQ). • This paper provides test cost reduction without increasing the defect level obviously. • We find the optimal solution between test cost and test quality. • KNN model was proposed to make it is possessed of stronger applicability and generality. • Test time and test quality have been greatly improved. [ABSTRACT FROM AUTHOR]

• The paper fills the gap in the literature by reviewing and analyzing the current studies that apply deep learning for Covid-19 forecasting. • The initial search identified 152 studies of which 53 passed the quality control. • The existing literature is categorized using a model-based taxonomy. • The description of the models along with their performance evaluation is presented. • Recommendations for future improvements are provided. The Covid-19 pandemic has galvanized scientists to apply machine learning methods to help combat the crisis. Despite the significant amount of research there exists no comprehensive survey devoted specifically to examining deep learning methods for Covid-19 forecasting. In this paper, we fill the gap in the literature by reviewing and analyzing the current studies that use deep learning for Covid-19 forecasting. In our review, all published papers and preprints, discoverable through Google Scholar, for the period from Apr 1, 2020 to Feb 20, 2022 which describe deep learning approaches to forecasting Covid-19 were considered. Our search identified 152 studies, of which 53 passed the initial quality screening and were included in our survey. We propose a model-based taxonomy to categorize the literature. We describe each model and highlight its performance. Finally, the deficiencies of the existing approaches are identified and the necessary improvements for future research are elucidated. The study provides a gateway for researchers who are interested in forecasting Covid-19 using deep learning. [ABSTRACT FROM AUTHOR]

In this paper, we study the performance of robust learning with Huber loss. As an alternative to traditional empirical risk minimization schemes, Huber regression has been extensively used in machine learning. A new comparison theorem is established in the paper, which characterizes the gap between the excess generalization error and the prediction error. In addition, we refine the error bounds from the perspective of statistical learning theory and improve the convergence rates in the presence of heavy-tailed noise. It is worth mentioning that a new moment condition E [ | Y | 1 + ∊ | X = x ] ∈ L ρ X 2 is employed in analysis of error bound and learning rates from a theoretical viewpoint. [ABSTRACT FROM AUTHOR]

Foreign species can deteriorate the environment and the economy of a country. To automatically monitor biosecurity threats at country borders, this paper investigates compact deep networks for accurate and real-time object segmentation for hyperspectral images. To this end, knowledge distillation (KD) approaches compress the model by distilling the knowledge of a large teacher network to a compact student network. However, when the student is over-compressed, the performance of standard KD methods degrades significantly due to the large capacity gap between the teacher and the student. This gap can be addressed by adding medium-sized teacher assistants, but training them incurs significant computation and hence is impractical. To address this problem, this paper proposes a new framework called Knowledge Distillation from Multi-head Teacher (KDM), which distills the knowledge of a multi-head teacher to the student. By encapsulating multiple teachers in a single network, our proposed KDM assists the learning of a very compact student and significantly reduces the training time. We also introduce Bio-HSI, a new large benchmark hyperspectral image dataset of 3,125 high-resolution images with dense segmentation ground truth. This new, large dataset can be expected to advance research on deep models for hyperspectral image segmentation. Evaluated on this dataset, the student trained via our KDM has 762 times fewer parameters than the state-of-the-art segmentation model (i.e., HRNet), while achieving competitive accuracy. [ABSTRACT FROM AUTHOR]

• The emerging dependency on Electric vehicles and the role of Machine Learning in bolstering it. • Hybrid techniques tend to outwit different approaches. • Comprehensive review of various battery life estimation techniques about Machine Learning and Deep Learning. • Challenges faced and future scope of Deep Learning and Machine Learning in the State of Charge, knee-point, and Remaining Useful Life prediction of Lithium-ion batteries. Rapid adoption in the usage of li-ion battery-fueled vehicles provides a promising approach to assuage the impact of climate change. The implementation and increasing sales trends in the Electric vehicle industry have created positive results in various regions. The reliability and consistency of the Battery management system in new-age Electric vehicles to predict the remaining battery cycles, State of charge, and knee point prove to be a complex task citing the non-linear behavior of lithium-ion batteries throughout their complete lifecycle. However, to make sure that the batteries work as intended consistently, there arises a need to monitor the battery's health and performance regularly. By examining recent literature, this paper carries out a comparative study of various published research regarding estimating the State of charge for Lithium-ion batteries using multiple methods, classified into three categories: adaptive, data-driven, and hybrid approaches. We also conducted a comparative study on Knee-point and the number of charge-discharge cycles left about electric vehicles. This review intends to furnish a comparative analysis of Machine learning & Artificial intelligence-related estimation techniques and analyze their superiority over traditional data-driven methods. It was observed that hybrid techniques consisting of various Machine learning algorithms yielded good results. This paper aims to perceive the most accurate algorithms and methodologies used, which can be further used in battery management systems to improve battery prognostics drastically. The future works and challenges encountered in various researches have also been mentioned at the end of the review that will hopefully pave the way for increasing efforts towards the development of the advanced SOC, knee point, and RUL methods for future EV uses. [ABSTRACT FROM AUTHOR]

Routing is one of the most important and time-consuming stages of physical design. As the process node of semiconductors keeps scaling down, the routing process faces increasing challenges, and the traditional solutions are not sufficiently efficient. In recent years, machine learning has aroused much interest in this context, and an increasing number of algorithms have introduced advanced machine learning techniques to help solve the routing problem. In this paper, we survey the recent development of machine learning-based routing algorithms. • This paper provides an overview of recent published machine learning-based routing algorithms. • Some trends on the development of machine learning-based routing algorithms are revealed. • The possible advantages and disadvantages on machine learning-based routing methods are discussed. [ABSTRACT FROM AUTHOR]

Two participants with competing objectives are considered in one-to-one orbital pursuit-evasion problem, one of which attempts to satisfy some certain terminal conditions with a minimum cost through its own control while the other player attempts to maximize the specified payoff and avoids entering this terminal range. This paper treats the problem of minimax time to a given final distance, within which the interception between pursuer and evader is defined to occur. To achieve the successful interception with an evader that adopts any unknown maneuvers, a near-optimal interception strategy for the orbital pursuit-evasion is presented in this paper. The pursuit-evasion problem is formulated as a differential game first, and a closed-form barrier solution is provided next. A near-optimal guidance law using deep learning is proposed to intercept the evader inside the capture zone. For the games that start outside the barrier, a learning algorithm for the capture zone embedding strategy is presented based on deep reinforcement learning to help the game state cross the barrier surfaces. The simulation cases of intercepting the evaders that adopt different maneuvering strategies are provided, and the results demonstrate the effectiveness and onboard feasibility of the proposed strategy in solving the orbital interception problem. • The closed-form barrier solution for a planar orbital pursuit-evasion game is provided. • A deep neural network is trained on a dataset consisting of plenty of barrier trajectories generated through the closed-form barrier formula. • The near-optimal guidance law inside capture zone is proposed using trained neural network. • A capture zone embedding strategy is presented based on deep reinforcement learning. • The closed loop interception strategy is proposed combining the strategies outside and inside capture zone. [ABSTRACT FROM AUTHOR]

This paper presents a review of up-to-date Machine Learning (ML) techniques applied to photovoltaic (PV) systems, with a special focus on deep learning. It examines the use of ML applied to control, islanding detection, management, fault detection and diagnosis, forecasting irradiance and power generation, sizing, and site adaptation in PV systems. The contribution of this work is three fold: first, we review more than 100 research articles, most of them from the last five years, that applied state-of-the-art ML techniques in PV systems; second, we review resources where researchers can find open data-sets, source code, and simulation environments that can be used to test ML algorithms; third, we provide a case study for each of one of the topics with open-source code and data to facilitate researchers interested in learning about these topics to introduce themselves to implementations of up-to-date ML techniques applied to PV systems. Also, we provide some directions, insights, and possibilities for future development. • Review of papers applying machine learning techniques to photovoltaic systems. • Review of open datasets, code, and simulation environments in photovoltaic systems. • More than 100 research articles reviewed with particular focus on deep learning. • Study cases with open source code for each one of the challenges. • Opportunities for future research and development. [ABSTRACT FROM AUTHOR]

A recent paper (Mhaskar (2020)) introduces a straightforward and simple kernel based approximation for manifold learning that does not require the knowledge of anything about the manifold, except for its dimension. In this paper, we examine how the pointwise error in approximation using least squares optimization based on similarly localized kernels depends upon the data characteristics and deteriorates as one goes away from the training data. The theory is presented with an abstract localized kernel, which can utilize any prior knowledge about the data being located on an unknown sub-manifold of a known manifold. We demonstrate the performance of our approach using a publicly available micro-Doppler data set, and investigate the use of different preprocessing measures, kernels, and manifold dimensions. Specifically, it is shown that the localized kernel introduced in the above mentioned paper when used with PCA components leads to a near-competitive performance to deep neural networks, and offers significant improvements in training speed and memory requirements. To demonstrate the fact that our methods are agnostic to the domain knowledge, we examine the classification problem in a simple video data set. • We examine the pointwise error in approximation using least squares optimization based on the kernel presented in Mhaskar (2020). • The approximation error depends upon the data characteristics and deteriorates as one goes away from the training data. • The theory is presented with an abstract localized kernel, which can utilize any prior knowledge about the data being located on an unknown sub-manifold of a known manifold. • We demonstrate the performance of this kernel using a publicly available micro-Doppler data set, investigating the use of different preprocessing measures, kernels, and manifold dimension. • It is shown that the proposed method offers nearcompetitive performance to deep neural networks and significant improvements to speed and accuracy. [ABSTRACT FROM AUTHOR]

In a dynamic environment, the moving obstacle makes the path planning of the manipulator very difficult. Therefore, this paper proposes a path planning with dynamic obstacle avoidance method of the manipulator based on a deep reinforcement learning algorithm soft actor-critic (SAC). To avoid the moving obstacle in the environment and make real-time planning, we design a comprehensive reward function of dynamic obstacle avoidance and target approach. Aiming at the problem of low sample utilization caused by random sampling, in this paper, prioritized experience replay (PER) is employed to change the weight of samples, and then improve the sampling efficiency. In addition, we carry out the simulation experiment and give the results. The result shows that this method can effectively avoid moving obstacles in the environment, and complete the planning task with a high success rate. [ABSTRACT FROM AUTHOR]

This paper overviews and discusses the relationship between Reinforcement Learning (RL) and the recently developed Dual Control for Exploitation and Exploration (DCEE). It is argued that there are two related but quite distinctive approaches, namely, control and machine learning, in tackling intractability arising in optimal decision making/control problems. In the control approach, the original problems (of an infinite horizon) are approximated by finite horizon problems and solved online by taking advantage of the availability of computing power. In the machine learning approach, the optimal solutions are approximated through iterations, or (offline) training through trials when models are not available. When dealing with unknown environments, DCEE as a technique developed from the control approach could potentially solve similar problems as RL while offering a number of advantages, most notably, coping with uncertainty in environment/tasks, high efficiency in learning through balancing exploitation and exploration, and potential in establishing its formal properties like stability. The links between DCEE and other relevant methods like dual control, Model Predictive Control and particularly Active Inference in neuroscience are discussed. The latter provides a strong biological endorsement for DCEE. The methods and discussions are illustrated by autonomous source search using a robot. It is concluded that DCEE provides a promising, complementary approach to RL, and more research is required to develop it as a generic theory and fully realise its potential. The relationships revealed in this paper provide insights into these relevant methods and facilitate cross fertilisation between control, machine learning and neuroscience for developing autonomous control under uncertain environments. [ABSTRACT FROM AUTHOR]

Identification through image processing has been used in various fields, including product examination and more recently infrastructure inspection, such as identifying cracks in structures. The conventional method, in which a human inspector uses a crack gauge or determines the size through a visual evaluation, results in a subjective evaluation of the extent of concrete life. Currently, an operator inspects the concrete structure by visually examining the concrete surface. However, this method presents numerous problems, including when the inspector has to work in dangerously high places. Therefore, we used machine learning to extract the features of cracks in image processing. We identified that non-arbitrary features, such as color-related features, are also important. Because concrete appears monochromatic, it is difficult for humans to analyze this color-related feature. We compared these newly obtained machine learning features with the previously used arbitrary features and confirmed that the machine learning features were more accurate in terms of detection. We also compared the generation of discriminators based on these features with a fixed threshold for discrimination and the utilization of support vector machine (SVM) and other machine learning methods. In this paper, two issues are discussed: an analysis of the effectiveness of machine learning and SVM-based discriminant generation in detecting cracks, and the classification results based on crack width. Crack width classification using machine learning is useful when sufficient image resolution is not available. The final detection accuracy of the new method was 11.7% better than that of the method using arbitrary features; moreover, the false detection rate was also higher in the proposed method. We further attempted to classify these cracks in accordance with their damage levels. To evaluate the degree of damage, we focused on the difference in the width of the cracks and extracted different features in three classes on the basis of the different crack widths, and were able to classify these clacks. • We used machine learning to extract the features of cracks. We identified that non-arbitrary features, such as color-related features, are also important. Because concrete is apparently monochromatic, it is difficult for humans to analyze this color-related feature. We compared these newly obtained machine learning features with the previously used arbitrary features and confirmed that the machine learning features were more accurate in detection.. • We compared the generation of discriminators based on these features with a fixed threshold for discrimination and the utilization of support vector machine (SVM). The final detection accuracy of the new method was 11.7% better than that of the method using arbitrary features; moreover, the false-positive rate was also higher in the proposed method.. • We attempted to classify these cracks according to their damage levels. To evaluate the degree of damage, we focused on the difference in the width of the cracks and extracted different features in three classes based on the different crack widths. In this paper, the following two issues are discussed: the first is an analysis of the effectiveness of machine learning and SVM-based discriminant generation in detecting cracks, and the second is the classification results based on crack width. Finally, we evaluated the degree of damage by classifying the cracks based on crack width using machine learning.. [ABSTRACT FROM AUTHOR]

• This paper explores the capabilities of machine-learning based fault detection and diagnosis. • The scope of the research is narrowed to the identification of transient events. • The K-Nearest Neighbors model achieved the highest accuracy of 97% in the primary system. The increasing interest in artificial intelligence and automation within the nuclear industry stems from the hope of elevating the safety and reliability of nuclear power plants by minimizing the impact of human errors. This paper explores the capabilities of machine-learning based fault detection and diagnosis (FDD) models in accurately classifying transient events in a nuclear power plant using the Classification Learners Application from MATLAB. The scope of the research is narrowed to the identification of transient events of the same nature occurring at various locations within the plant. To accomplish this, the Generic Pressurized Water Reactor (GPWR) from the Western Services Cooperation (WSC) was used to simulate 14 transients in the primary system and 10 transients in the secondary system, resulting in two distinct datasets of 108,000 and 79,200 observations. Nine types of classifiers, including Decision Trees, Discriminant Analysis, Support Vector Machines, Logistic Regression, Nearest Neighbors, Naive Bayes, Kernel Approximation, Ensembles, and Neural Networks, with a total of 33 predefined models, were trained and validated. The K-Nearest Neighbors model achieved the highest accuracy of 97% in the primary system, while the Efficient Linear Discriminant and Logistic Regression models achieved the highest average accuracy of 99% in the secondary system. The assessment of the top-performing models was conducted through a comprehensive analysis employing key classification model evaluation metrics, such as the confusion matrix, accuracy, precision, recall, and the F1 score. In an effort to optimize the models, the study integrated feature selection using the minimum Redundancy Maximum Relevance (mRMR) algorithm. Additionally, the investigation explored different validation schemes, including both holdout and k-fold cross-validation schemes, resulting in a substantial reduction in training time without significantly compromising the overall accuracy of the models. The optimized models in this study demonstrated remarkable prediction accuracies, consistently exceeding 94%. Despite the complexity of the models and the intricacies involved in the training process, the training times ranged from 10 to 1800 s, reflecting the efficiency and robustness of the implemented optimization techniques. The results of this study underscore the potential of machine learning models in identifying transient events in nuclear reactors, showcasing their promising capabilities while maintaining low computational and execution costs. This suggests their efficacy in optimizing safe and efficient operational practices within nuclear facilities. [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]

The emergence of online social networks (OSN) platforms removes communication barriers that are essential to human life, catalyzing social networking growth. However, this emergence has given rise to a negative impact when someone abuses the platform to commit cyberbullying activities. Hence, it is crucial to work on automated cyberbullying-related classification to mitigate the societal phenomena in OSN. The research on the automated classification model for cyberbullying was pioneered over the last decade with growing interest among researchers. It is helpful to track its growth over the decades to elucidate the state-of-arts techniques applied in this field. This paper presents a large amount of literature germane to cyberbullying classification from past to present to provide a comprehensive review. A total of 126 papers were reviewed. This paper emphasizes text-based cyberbullying and multi-modal cyberbullying. The review was presented around the machine learning workflow, encompassing four core sections: dataset analysis, pre-processing analysis, feature analysis, and technique analysis. Based on the critical analysis, limitations are addressed along with the future works that can be conducted to fill the gap in previous research. Furthermore, the review also examined the ethical implications associated with the implementation of these techniques. This review paper is expected to assist readers in fully comprehending the current trend, architecture, and techniques applied to the field. [ABSTRACT FROM AUTHOR]

Modern machine learning algorithms aim to extract fine-grained information from data to provide accurate predictions, which often conflicts with the goal of privacy protection. This paper addresses the practical and theoretical importance of developing privacy-preserving machine learning algorithms that ensure good performance while preserving privacy. In this paper, we focus on the privacy and utility (measured by excess risk bounds) performances of differentially private stochastic gradient descent (SGD) algorithms in the setting of stochastic convex optimization. Specifically, we examine the pointwise problem in the low-noise setting for which we derive sharper excess risk bounds for the differentially private SGD algorithm. In the pairwise learning setting, we propose a simple differentially private SGD algorithm based on gradient perturbation. Furthermore, we develop novel utility bounds for the proposed algorithm, proving that it achieves optimal excess risk rates even for non-smooth losses. Notably, we establish fast learning rates for privacy-preserving pairwise learning under the low-noise condition, which is the first of its kind. [ABSTRACT FROM AUTHOR]

[Display omitted] • Integrating deep learning with 2DCOS for wheat flour spectral classification. • The improved EfficientNet model achieved 100% accuracy in wheat flour identification. • Comparison of deep learning and machine learning methods in spectral analysis. • Transforms spectra into images, applicable beyond wheat flour. Wheat flour is a ubiquitous food ingredient, yet discerning its various types can prove challenging. A practical approach for identifying wheat flour types involves analyzing one-dimensional near-infrared spectroscopy (NIRS) data. This paper introduces an innovative method for wheat flour recognition, combining deep learning (DL) with Two-dimensional correlation spectrum (2DCOS). In this investigation, 316 samples from four distinct types of wheat flour were collected using a near-infrared (NIR) spectrometer, and the raw spectra of each sample underwent preprocessing employing diverse methods. The discrete generalized 2DCOS algorithm was applied to generate 3792 2DCOS images from the preprocessed spectral data. We trained a deep learning model tailored for flour 2DCOS images – EfficientNet. Ultimately, this DL model achieved 100% accuracy in identifying wheat flour within the test set. The findings demonstrate the viability of directly transforming spectra into two-dimensional images for species recognition using 2DCOS and DL. Compared to the traditional stoichiometric method Partial Least Squares Discriminant Analysis (PLS_DA), machine learning methods Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), and deep learning methods one-dimensional convolutional neural network (1DCNN) and residual neural network (ResNet), the model proposed in this paper is better suited for wheat flour identification, boasting the highest accuracy. This study offers a fresh perspective on wheat flour type identification and successfully integrates the latest advancements in deep learning with 2DCOS for spectral type identification. Furthermore, this approach can be extended to the spectral identification of other products, presenting a novel avenue for future research in the field. [ABSTRACT FROM AUTHOR]

• The proposed AP-GAN-DNN method is able to predict creep fracture life more accurately in the case of small samples, which solves the complex nonlinear problem and the problem of test data dispersion. • Compared with traditional physical methods and machine learning models, the AP-GAN-DNN model has better generalization and robustness for creep fracture life prediction. • AP-GAN data enhancement method can significantly reduce the "pattern collapse" effect of GAN and improve the performance of prediction algorithms. 7050 aluminum alloy has high strength and excellent fracture toughness. However, damage can be caused to the 7050 aluminum alloy by creep at elevated temperatures. The accuracy of conventional creep life prediction methods may fall short of meeting the desired standards. And the application of machine learning (ML) methods is limited due to the scarcity and dispersion of creep sample data. Generative Adversarial Networks (GAN) are often used for data enhancement, but suffer from "pattern collapse" under small sample conditions. To solve the above problems, this paper proposes a creep fracture life prediction method, which combines the affinity propagation (AP) clustering algorithm, GAN, and deep neural networks (DNN) for accurate creep fracture life prediction. The AP clustering algorithm for adaptive clustering was utilized to better reflect the creep sample distribution. Independent GAN models were trained for each cluster to better capture distribution characteristics of the data and generate synthetic data that was highly similar to the real data. The DNN models were trained using the synthetic data and then predicted using real creep fracture life data. The presented method was compared with traditional physical and machine learning methods, and the method combining K-Means, GAN, and DNN. The experimental results show that the method proposed in this paper has better prediction accuracy in a small sample creep fracture life dataset. [ABSTRACT FROM AUTHOR]

The digitization of the water sector has led to the emergence of Smart Water Metering Networks (SWMNs), which enable automated and continuous water consumption measurement. However, challenges persist in efficiently managing and transmitting the vast amount of data generated by these networks. To address this, researchers have proposed anomaly detection techniques to identify and detect anomalies within SWMNs. In the realm of anomaly detection, a substantial body of research has emerged. However, there is a notable gap in the literature on a comprehensive synthesis of Machine Learning (ML) applications for anomaly detection in SWMNs. To bridge this knowledge gap, this study evaluated thirty-two research papers written between 2016 and 2023, focusing on ML applications for anomaly detection in smart water systems, smart water grids, water distribution networks, and water networks. From an initial pool of 725 research papers, those directly related to ML-based anomaly detection techniques were selected and analysed using both quantitative and qualitative data analysis. The study revealed that ML techniques such as k-Nearest Neighbors (kNN), Autoencoders, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Random Forest, Decision Trees, and Support Vector Machines (SVM) have made significant contributions to anomaly detection within these networks. Notably, researchers frequently employed multiple ML techniques to enhance accuracy. Performance metrics analysis demonstrated that F1 score, precision, accuracy, and recall were commonly used to assess the quality of ML anomaly detection techniques. This review aims to provide researchers with recommendations for selecting suitable ML anomaly detection techniques in SWMNs. The findings underscore the promising nature of ML applications for anomaly detection in SWMNs and highlight the need for further research in this area. • Water networks use Cyber Physical Systems, leveraging adaptability for benefits. • Machine Learning (ML) detects diverse anomalies in Water Networks effectively. • Data availability crucial for robust ML anomaly detection in Water Networks. • ML techniques enable real-time anomaly detection, identifying Water Network issues. • Research on ML anomaly detection in SWMNs lacks systematic literature review. [ABSTRACT FROM AUTHOR]

Property valuation research, evolving with Automated Valuation Models (AVMs) using Artificial Intelligence (AI) and Machine Learning (ML), encounters challenges in handling dynamic market conditions. While the market approach is a practical solution to complement the AVMs, it also suffers from different deficiencies, particularly in relying on subjective valuer judgment. In Australia's diverse real estate market, complete and up-to-date market data derived from recent transactions of the different property types within various suburbs can be crucial for valuers. However, accessing such data often comes at a high cost, and the availability of transaction data is limited, mainly when market analysis necessitates the consideration of property valuation across various property types and bedroom counts. Accordingly, this paper presents a novel multi-step method to estimate the median prices of different property types considering their bedroom counts at the suburban level in the Melbourne Metropolitan area to benefit valuers when adopting the market approach. Nine distinct and ensembled spatially-based imputation techniques of K-Nearest Neighbors (KNN), Inverse Distance Weighted (IDW), Weighted KNN, Weighted IDW, Weighted KNN-IDW, Random Forest (RF), eXtreme Gradient Boosting (XGBoost), RF-IDW-KNN and XGBoost-IDW-KNN are first employed to impute missing data on six market-related parameters obtained from the Real Estate Institute of Victoria (REIV). These parameters include median price (with no consideration of bedroom counts), price change, median rent, rental yield, clearance rate and days on market for houses and units. Next, based on these parameters, three ML algorithms—RF, Support Vector Regression (SVR) and XGBoost—are developed to estimate the median prices. Subsequently, the Long Short-Term Memory (LSTM) technique is employed for Deep Learning (DL)-based spatiotemporal analysis, clustering suburbs based on property value fluctuations. Finally, these clusters are integrated into the ML models developed in the previous step as an auxiliary feature to assess their potential impact on enhancing price estimation accuracy. The results demonstrate promising accuracies for different property types based on different performance assessment metrics. The paper also underscores improved estimation accuracy by incorporating time series-based clustering as a supplementary parameter through transfer learning. [ABSTRACT FROM AUTHOR]

Tunnel Boring Machine (TBM) construction, particularly with closed-face TBMs, faces uncertainties due to the inability of the operator to directly observe the ground ahead. These uncertainties can lead to time delays, cost overruns, and accidents. While supervised machine learning techniques have been used to predict geology from TBM sensor data, their performance drops significantly when applied to other projects, indicating poor generalization. To ensure accurate results and improved generalization to future data, supervised learning models require high-quality, well-labeled data which is not usually the case for TBM datasets. This paper addresses the issue of "noisy" labels in TBM datasets, which human operators and engineers often label with varying interpretations. A data-centric framework was adapted and applied to an Earth Pressure Balance Machines (EPBM) tunnel dataset to detect and identify these mislabeled datapoints. The framework's outputs were validated using two techniques and apply several methods to clean the dataset. The best-performing method was selected for the test set. The paper concludes by discussing the limitations of the proposed method, the challenges encountered, and future research directions in this area. [ABSTRACT FROM AUTHOR]

The key component of designing sustainable, enriching, and inclusive cities is public participation. The soundscape is an integral part of an immersive environment in cities, and it should be considered as a resource that creates the acoustic image for an urban environment. For urban planning professionals, this requires an understanding of the constituents of citizens' emergent soundscape experience. The goal of this study is to present a systematic method for analyzing crowdsensed soundscape data with unsupervised machine learning methods. This study applies a crowdsensed sound- scape experience data collection method with low threshold for participation. The aim is to analyze the data using unsupervised machine learning methods to give insights into soundscape perception and quality. For this purpose, qualitative and raw audio data were collected from 111 participants in Helsinki, Finland, and then clustered and further analyzed. We conclude that a machine learning analysis combined with accessible, mobile crowdsensing methods enable results that can be applied to track hidden experiential phenomena in the urban soundscape. [Display omitted] • The goal of this paper is to present a systematic method for analyzing crowdsensed soundscape data with unsupervised machine learning methods • Mobile crowdsensing methods for data collection and machine learning analysis enabled a method which could be applied to tracking hidden experiential phenomena from urban soundscape. • The end-to-end method presented in this paper opens possibilities to efficiently and smartly study soundscapes in different contexts. [ABSTRACT FROM AUTHOR]

One key driver of sustainable goal development is the transition to sustainable electricity resources. The sustainability impact assessment of power production evaluates all potential impacts on society, the environment, and the economy, as well as finds a reasonable solution to shift towards renewable. Given the multitude of quantitative and qualitative methodologies for sustainability analysis, alongside the absence of a unified procedure, selecting an appropriate method poses a significant challenge in conducting this task. Therefore, this paper conducts an extensive review of the methodologies employed for assessing the sustainability of power generation within the future energy mix, as reflected in scientific publications over the past decade (2013–2024). The main objective of this paper is to compare the methodologies and assess their efficiency as suitable tools for analyzing the sustainability of technologies in different geographical regions. The research methodology, following the screening process, selects 102 papers within the study's scope to undergo a critical examination based on sustainability evaluation approaches. It also provides an overview of novel dynamic methods and the application of artificial intelligence in sustainability assessment. The primary findings indicate a deficiency in a standardized approach for sustainability evaluation within electrical technology. In addressing uncertainties in impact assessment due to various parameters, dynamic methods with multiple temporal accuracies are recommended over a static life cycle. The paper includes a case study comparing methods—multi-criteria decision-making, and ranking, scoring—in the Indonesian context. Considering 15 environmental, social, and economic indicators to evaluate the sustainability in Lombok, results indicate that hydropower, gas, and solar technologies exhibit the highest sustainability scores, respectively. [ABSTRACT FROM AUTHOR]

With the development of digital technology, the maritime industry is under continuous digital transformation. For example, from manned engine room to control room and even to remotely controlled or autonomous ships. Maintenance has also changed from being a reactive or scheduled procedure to a predictive and proactive activity. Proactive maintenance relies on the condition monitoring (CM) of equipment. Condition Based Maintenance (CBM), Reliability Centered Maintenance (RCM) and Prognostics and Health Management (PHM) primarily focusing on three technical processes, namely condition monitoring, fault diagnosis and prognosis, and maintenance decision-making. Over the recent years, research has been on these topics through two main approaches: data-driven approaches and model-based approaches. Especially data-driven approaches with Deep Learning (DL) techniques have become a popular direction with successful implementation in different domains. Classification Societies are also developing new standards and methods with the industry to provide assurance of these emerging services. This paper presents a comprehensive review of state-to-art methods for PHM techniques for the past few years (2017–2023). First, a general introduction to different approaches with a focus on data-driven methods is presented. Subsequently, a detailed review of techniques applied to PHM is provided, where unique contributions, advantages, limitations and challenges are discussed. This is followed by a chapter that discusses the technical rules and standards from classification societies (DNV and ABS). The paper then explores the benefits, challenges, existing problems, and recommendations for PHM from the perspective of classification societies. Maritime stakeholders may find this article to be a valuable guide or reference for the development of such services. • A comprehensive review of PHM in the maritime industry is implemented. • Evaluation of diverse PHM methodologies like physics-based, and data-driven methods. • Introduced a new categorization and data flow analysis for the reviewed PHM papers. • Reviewed DNV and ABS rules on PHM, summarizing classification societies' insights. • Presented challenges and future opportunities for PHM in maritime from DNV's view. [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]

This paper explores consumer green consumption practices and considers a set of factors, including cognitive and behavioural level constructs, that influence green consumption. The paper primarily aims to predict the green purchase intention and classify a consumer as a green or non-green consumer. A total of 310 responses were collected and analyzed using machine Learning techniques like Decision Tree, Random Forest, Gradient Boosting, XGBoost, K-Nearest Neighbour, and Support Vector Machine, and the models were validated using different performance metrics. The paper reveals that the main driving factors for a consumer to consider greener options are green self-identification, followed by environmental knowledge, environmental consciousness, and the impact of social media. The current work will allow better product development and the targeting and positioning of green products/services offerings to customers already classified by the system. • Machine learning techniques were employed to predict green purchase intention (GPI). • Green Self-identification & Environmental Consciousness were the crucial factors in influencing GPI. • Social and health consciousness had less of an impact on influencing GPI. • Perceived personal inconvenience was reported to have no significant impact on GPI. [ABSTRACT FROM AUTHOR]

A multi-layer neural network is used to extract the value of a superconductor's T c of cuprate from two models. The first model extracts T c from the structure's chemical composition whereas the second model extracts T c from the structure's chemical composition and the lattice parameters. The back-propagation algorithm is used to find the empirical equation of T c. It can calculate error signals and redistribute backward propagation signals. This paper studies four systems of cuprate superconductors: Y Ba Cu O, Bi Sr Ca Cu O, Tl Ba Ca Cu O, and Hg Ba Ca Cu O. In the first model, the T c of four high-temperature oxide superconductors are calculated as a function of eight parameters and one output, which is T c. Although the same output is produced in the second model, it is produced as a function of eleven parameters. The eight parameters are superconductor type number (Bi2212, Bi2223, Hg1201, Hg1212, Hg1223, Y123, Y124, Y247, Tl1223, Tl2212, Tl2223), first component composition, second component composition, third component composition, fourth component composition, atomic number of doping type, doping composition, and oxygen composition of the first model. The previous parameters with the three lattice parameters a , b and c are used in the second model. The trained deep learning models have shown a high degree of performance in matching the trained distributions. After analysing the results, we deduce electronegativity plays an important role in increasing T c of cuprate superconductors. Using the obtained T c prediction model, the scope is expanded to include the eleven unexplored multi-element materials. Candidates for superconductors with a higher T c that can be synthesized are proposed. By comparison with other models of machine learning, the suggested models in this paper give the highest T c for predicting new cuprate superconductors. [ABSTRACT FROM AUTHOR]

Hydrogen, as a clean and efficient energy source, is important in achieving zero-CO 2 targets. This paper explores the potential of hydrogen geologic storage (HGS) in China for large-scale energy storage, crucial for stabilizing intermittent renewable energy sources and managing peak demand. Despite its promise, HGS faces challenges due to hydrogen's low density and viscosity, and its complex interactions with geological formations and microorganisms. This review offers a comprehensive overview of the current research status for HGS, with a particular focus on highlighting the main challenges confronting China. These difficulties and challenges primarily arise from complex geological conditions and the absence of fundamental parameters within potential reservoirs, including depleted oil/gas fields, salt caverns, and brine aquifers. Additionally, we have synthesized the current applications of machine learning (ML)as a potential solution. Key challenges are examined, such as the effects of operational parameters (e.g., cyclical injection-production and injection rates) on HGS efficiency, which can influence phenomena such as hydrogen fingering and caprock integrity. This review also looks into the insufficiently understood hydrogen-water-rock geochemical reactions under diverse temperatures and pressures, a gap that hampers the development of predictive numerical simulations and raises concerns about hydrogen leakage due to changes in porosity and permeability. Additionally, the paper addresses the limited knowledge about the metabolic mechanisms of subsurface microorganisms under extreme conditions, highlighting potential risks of hydrogen leakage and groundwater contamination. These microorganisms can metabolize hydrogen, producing gases such as CH 4 and H 2 S, which may cause steel corrosion. Furthermore, the study assesses the distribution and prospects of three primary methods for pure hydrogen storage in China, considering the current state of hydrogen development and relevant government policies. The role of ML in advancing HGS is also discussed, offering insights into future research directions. This review not only scrutinizes the scientific challenges of HGS but also underscores its potential, guiding future simulation and practical engineering applications in this field. • HGS is feasibility in China through policy examination and potential site analysis. • Geochemical and microbial reactions jeopardize to reservoir integrity and H 2 quality. • Elucidating the present application and future prospective for ML in HGS. • Summarizing the key challenges associated with achieving large-scale HGS. [ABSTRACT FROM AUTHOR]

Knowledge of displacement responses of high-rise buildings under harsh wind excitations is essential for their wind-resistant structural design. This paper develops a machine learning model named long short-term memory (LSTM) to estimate the displacements of a 420-m-high building during Super Typhoon Mangkhut based on available field measurements. The developed model is trained and validated using the field measurements on the building during typhoon events, and the performance of the model is assessed against several evaluation criteria. Then, the trained LSTM model is employed to estimate the displacements of the skyscraper during Mangkhut. The accuracy of the estimated displacements is validated in time and frequency domains. Moreover, the background and resonant components of the estimated displacements during the extreme windstorm are analyzed. This paper aims to provide valuable reference for the wind-resistant design of high-rise buildings in tropical cyclone-prone regions. • Develop an LSTM model to estimate displacement responses of a 420-m-high building During Super Typhoon Mangkhut. • Examine effectiveness and accuracy of the developed LSTM model based on field measurements on the building during typhoons. • Estimate displacements of the skyscraper during Super Typhoon Mangkhut based on the LSTM model and available measurements. • Explore across-wind and along-wind responses, along with resonant and background components of the estimated displacements. [ABSTRACT FROM AUTHOR]

Truck drivers are essential to modern supply chains. However, the companies that employ them are having trouble keeping them. At many trucking firms, annual turnover rates approach 100 percent or higher. This paper develops a method for predicting individual truck driver turnover events before they happen by applying supervised machine learning classifiers to a new source of operational truck driver data. Our paper uses Electronic Logging Device (ELD) data, which comprise newly federally-mandated, time-stamped work logs collected from approximately 1200 American long-haul truck drivers over 3 years. We train three supervised machine learning classifiers (logistic regression, random forests, and support vector machines) on this data and achieve 60 to 70 percent prediction accuracy and 50 to 60 percent recall across two 5-fold cross-validated experiments. We observe that the quantity and consistency of week-day driving assignments explain most of our models' predictive power. We offer these results as both a new technical tool, as well as novel managerial insights for improving global truck driver retention problems for the benefit of supply chains worldwide. [Display omitted] • Newly available operational data from long haul truck drivers is analyzed. • Three machine learning classifiers are trained on the operational data. • Predictive models achieve 60–70 percent accuracy, 50–60 percent recall. • Models show potential to enable interventions to retain truck drivers. [ABSTRACT FROM AUTHOR]

This review reports a quantitative analysis across the deterministic photovoltaic (PV) power forecasting approaches. Model accuracy tests from papers passing a set of selection criteria are collected in a database, along with the meta-information necessary to describe the forecast scenarios. The selection criteria ensure a framework for inter-comparison analyses. 66 papers were found that pass the selection stage, constituting an arbitrary sample of the literature in terms of forecast scenario. Therefore, this review generates a reliable picture of the state-of-the-art in the accuracy of deterministic PV power forecasting. Despite the apparent wealth of the forecasting studies, a detailed analysis is foreclosed by the small number of entries into the database for different scenarios. Simple and hybrid Machine Learning models are the most popular choice. Studies performed in Europe, Asia and North America are dominant, with the majority of locations having a temperate climate (46/66). The number of studies in arid (10/66) and tropical (8/66) climates is small, even with the high speed development of the PV sector. Physics-based models are weakly represented. A set of recommendations on reporting the results of deterministic forecasts and metadata is proposed. A detailed description of forecast scenarios, employed accuracy metrics, and all operations applied on the data is crucial for ensuring a realistic inter-comparability of models' performance. • A quantitative analysis across PV power forecasting scenarios is performed. • nRMSE, MAPE and skill score are collected from 66 studies. • Model class, climate and forecast timescales are the most influential factors. • Test set length, metric normalization and other parameters impede inter-comparability. • Numerous gaps and biases found, despite apparent wealth of publications. [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]