Search

In the domain of modern manufacturing, computer numerical control (CNC) milling machines have emerged as instrumental assets. However, the data they generate is of vast amount, but usually contains redundancies and displays consistent patterns, making it inefficient for deep learning training. This paper proposes a novel sampling algorithm tailored for CNC milling machine data, emphasizing both diversity and efficiency. The proposed method leverages the entropy concept from the information‐theoretic perspective to evaluate and enhance data diversity, aiming to achieve efficient learning with high accuracy. This in turn enables to not only facilitates a deeper understanding of CNC data characteristics but also contributes significantly to the optimization of deep learning training processes in the context of CNC milling data. [ABSTRACT FROM AUTHOR]

Economic growth, air pollution, and forest fires in some states in the United States have increased the concentration of particulate matter with a diameter less than or equal to 2.5 μm (PM2.5). Although previous studies have tried to observe PM2.5 both spatially and temporally using aerosol remote sensing and geostatistical estimation, they were limited in accuracy by coarse resolution. In this paper, the performance of machine learning models on predicting PM2.5 is assessed with linear regression (LR), decision tree (DT), gradient boosting regression (GBR), AdaBoost regression (ABR), XGBoost (XGB), k‐nearest neighbors (K‐NN), long short‐term memory (LSTM), random forest (RF), and support vector machine (SVM) using PM2.5 station data from 2017 to 2021. To compare the accuracy of all the nine machine learning models, the coefficient of determination (R2), root mean square error (RMSE), Nash‐Sutcliffe efficiency (NSE), root mean square error ratio (RSR), and percent bias (PBIAS) were evaluated. Among all nine models, the RF (100 decision trees with a max depth of 20) and support vector regression (SVR; nonlinear kernel, degree 3 polynomial) models were the best for predicting PM2.5 concentrations. Additionally, comparison of the PM2.5 performance metrics displayed that the models had better predictive behavior in the western United States than that in the eastern United States. Key Points: We present the prediction of PM2.5 concentrations over the United States using various machine learning (ML) algorithmsWe show ML as a new approach for analyzing large data sets due to the computational speed and easy implementation for massive amounts of dataThe study is important for improving our understanding of the differences among ML algorithms for Earth Science research [ABSTRACT FROM AUTHOR]

The field of artificial intelligence is seeing the increased application of satellite imagery to analyse poverty in its various manifestations. This nascent but rapidly growing intersection of scholarship holds the potential to help us better understand poverty by leveraging big data and recent advances in machine vision. In this study, we statistically analyse the literature in the expanding field of welfare and poverty predictions from the combination of machine learning and satellite imagery. Here, we apply an integrative review method to extract key data on factors related to the predictive power of welfare. We found that the most important factors correlated to the predictive power of welfare are the number of pre‐processing steps employed, the number of datasets used, the type of welfare indicator targeted and the choice of AI model. Studies that used stock measure indicators (assets) as targets achieved better performance—17 percentage points higher—in predicting welfare than those that targeted flow measures (income and consumption) ones. Additionally, we found that the combination of machine learning and deep learning significantly increases predictive power—by as much as 15 percentage points—compared to using either alone. Surprisingly, we found that the spatial resolution of the satellite imagery used is important but not critical to the performance as the relationship is positive but not statistically significant. These findings have important implications for future research in this domain and for anyone aspiring to use the methodology. [ABSTRACT FROM AUTHOR]

Wastewater‐based epidemiology (WBE) has been proven to be a useful tool in monitoring public health‐related issues such as drug use, and disease. By sampling wastewater and applying WBE methods, wastewater‐detectable pathogens such as viruses can be cheaply and effectively monitored, tracking people who might be missed or under‐represented in traditional disease surveillance. There is a gap in current knowledge in combining hydraulic modeling with WBE. Recent literature has also identified a gap in combining machine learning with WBE for the detection of viral outbreaks. In this study, we loosely coupled a physically‐based hydraulic model of pathogen introduction and transport with a machine learning model to track and trace the source of a pathogen within a sewer network and to evaluate its usefulness under various conditions. The methodology developed was applied to a hypothetical sewer network for the rapid detection of disease hotspots of the disease caused by the SARS‐CoV‐2 virus. Results showed that the machine learning model's ability to recognize hotspots is promising, but requires a high time‐resolution of monitoring data and is highly sensitive to the sewer system's physical layout and properties such as flow velocity, the pathogen sampling procedure, and the model's boundary conditions. The methodology proposed and developed in this paper opens new possibilities for WBE, suggesting a rapid back‐tracing of human‐excreted biomarkers based on only sampling at the outlet or other key points, but would require high‐frequency, contaminant‐specific sensor systems that are not available currently. Plain Language Summary: Viral outbreaks such as COVID‐19 are commonly monitored using traditional surveillance methods (e.g., nose swabs). However, individuals may not follow such testing schemes for different reasons, such as if they do not have symptoms. When people are infected by COVID‐19, they excrete SARS‐CoV‐2, the virus that causes the disease. Hence, analyzing sewage using wastewater‐based epidemiology (WBE) methods could help monitor the virus outbreak. Recent literature has identified a gap in combining machine learning and hydraulic models with WBE to detect viral outbreaks. In this study, we combine a hydraulic model that simulates virus transport with a machine learning model that tracks hotspot areas within a sewer network. The methodology developed in this paper was applied to a hypothetical sewer network to detect COVID‐19 disease hotspots rapidly. Results showed that the machine learning model has the potential to recognize hotspots but requires high time‐resolution data and is dependent on the sewer system's characteristics, such as flow velocity and virus sampling procedure. The developed methodology opens new possibilities for WBE to potentially trace human‐excreted viral genetic material based on only sampling at particular points. However, it would require high‐frequency sampling sensor systems that are not available currently. Key Points: Using a numerical model of wastewater network and machine learning has the potential for the early detection of viral outbreaksThe ability to recognize disease hotspots depends on sampling frequency and methodThe use of sewer models can improve the usefulness of wastewater‐based epidemiology data [ABSTRACT FROM AUTHOR]

With the surge of searching and reading online health‐based articles, maintaining the quality and credibility of online health‐based articles has become crucial. The circulation of deceptive health information on numerous social media sites can mislead people and can potentially cause adverse effects on people's health. To address these problems, this work uses deep learning approaches to automate the assessment and scoring of online health‐related articles' credibility. The paper proposed an Attention‐based Recurrent Multichannel Convolutional Neural Network (ARMCNN) model. The proposed model incorporates a BiLSTM layer, a multichannel CNN layer, and an attention layer and predicts the credibility of online health information. To perform a reliable evaluation of the presented model, we utilize the health articles reviewed by the experts, compiled in a labeled dataset termed "Pubhealth," which consists of thousands of health articles. The results are evaluated using five performance measures, accuracy, precision, recall, f1‐score, and area under the ROC curve (AUC). Furthermore, we extensively compared the proposed model with different deep learning and machine learning models such as Long short‐term memory (LSTM), Bidirectional LSTM, CNN (Convolutional neural network), and RNN‐CNN. The experimental results showed that the proposed model produced state‐of‐the‐art performance on the used dataset by achieving an accuracy of 0.88, precision of 0.92, recall of 0.87, f1‐score of 0.90, and AUC of 0.94. Further, the proposed model yielded better performance than other benchmarked techniques for the credibility assessment of online health articles. [ABSTRACT FROM AUTHOR]

Decision‐makers and stakeholders require a rapid assessment of potential damage after earthquake events in order to develop and implement disaster risk reduction strategies and to respond systematically in post‐disaster situations. The damage investigated manually after an earthquake are complicated, labor‐intensive, time‐consuming, and error prone process. The development of fragility curves is time consuming and unable to predict the damage for wide classes of structures since it considers few structural properties and only one seismic characteristic. Furthermore, the nonlinear finite element method cannot be utilized for numerous buildings because it involves more time and money. This paper presents the machine learning (ML)‐based seismic damage prediction of RC buildings. It is found that some of the research works only considered seismic parameters or structural parameters to train the ML models and predict the structural damage assessment. However, these ML models may not fully reveal the underlying complexity of the relationship between input parameters and building performance. As a result, their applicability will be limited. This paper evaluates the feasibility of using ML techniques such as K‐nearest neighbor, random forest, decision tree, support vector machine, and artificial neural network to rapidly predict earthquake‐induced reinforced concrete building damage considering both the structural properties and ground motion characteristics. The machine learning models are trained using the simulation results. Due to lack of real earthquake damage datasets or limited access, most of the research works used Scikit Learn train_test_split function to randomly split the entire datasets into training and testing datasets and the performance of the proposed ML technique are evaluated using the testing datasets. However, in this study, the performances of different ML models are evaluated using real earthquake damage datasets of RC buildings collected after 2015 Nepal earthquake. The overall accuracy on testing datasets suggests the capability of machine learning algorithms in successfully predicting the seismic damage of reinforced concrete buildings in quick time with reasonable accuracy. This study is beneficial in emergency response and recovery planning after an earthquake. [ABSTRACT FROM AUTHOR]

Progression‐free survival (PFS) is an important clinical metric for comparing and evaluating similar treatments for the same disease within oncology. After the completion of a clinical trial, a descriptive analysis of the patients' PFS is often performed post hoc using the Kaplan–Meier estimator. However, to perform predictions, more sophisticated quantitative methods are needed. Tumor growth inhibition models are commonly used to describe and predict the dynamics of preclinical and clinical tumor size data. Moreover, frameworks also exist for describing the probability of different types of events, such as tumor metastasis or patient dropout. Combining these two types of models into a so‐called joint model enables model‐based prediction of PFS. In this paper, we have constructed a joint model from clinical data comparing the efficacy of FOLFOX against FOLFOX + panitumumab in patients with metastatic colorectal cancer. The nonlinear mixed effects framework was used to quantify interindividual variability (IIV). The model describes tumor size and PFS data well, and showed good predictive capabilities using truncated as well as external data. A machine‐learning guided analysis was performed to reduce unexplained IIV by incorporating patient covariates. The model‐based approach illustrated in this paper could be useful to help design clinical trials or to determine new promising drug candidates for combination therapy trials. [ABSTRACT FROM AUTHOR]

Forecasting complex time series faces a huge challenge due to its high volatility. To improve the accuracy and robustness of prediction, this paper proposes a bi‐level ensemble learning approach by combining decomposition‐ensemble forecasting and resample strategies. The bi‐level ensemble approach consists of four steps: data decomposition via singular spectrum analysis (SSA), resampling by employing a bagging algorithm, individual forecasting utilizing extreme learning machine (ELM), and introducing sorting‐pruning and simple addition ensemble strategies for integrating the inner and outer results, respectively. To verify the effectiveness of the established forecasting approach, three exchange rate time series are selected as samples. The results reveal that the proposed model is significantly better than the other benchmarks at different lead times, which indicates that it can be regarded as an effective and promising tool for complex time series forecasting. [ABSTRACT FROM AUTHOR]

Frozen sections are a useful pathologic tool, but variable image quality may impede the use of artificial intelligence and machine learning in their interpretation. We aimed to identify the current research on machine learning models trained or tested on frozen section images. We searched PubMed and Web of Science for articles presenting new machine learning models published in any year. Eighteen papers met all inclusion criteria. All papers presented at least one novel model trained or tested on frozen section images. Overall, convolutional neural networks tended to have the best performance. When physicians were able to view the output of the model, they tended to perform better than either the model or physicians alone at the tested task. Models trained on frozen sections performed well when tested on other slide preparations, but models trained on only formalin‐fixed tissue performed significantly worse across other modalities. This suggests not only that machine learning can be applied to frozen section image processing, but also use of frozen section images may increase model generalizability. Additionally, expert physicians working in concert with artificial intelligence may be the future of frozen section histopathology. [ABSTRACT FROM AUTHOR]

The popularity of the Internet of Things (IoT) makes a large number of vulnerable devices connected to the Internet, which brings a large number of digital multimedia signals. How to process these digital multimedia signals and ensure the security in IoT has become an important topic in the IoT applications and services. With the development of data analysis and artificial intelligence, the IoT devices present intelligent behaviors and become the new generation of information infrastructure. This paper proposed a framework to process the digital signals generated by IoT devices and ensure the IoT security. First, the original traffic data passes through the security gateway and the associated traffic data is collected by a damping window. Second, the collected traffic data is processed by a feature analysis module to construct a fingerprint library. Third, the fingerprint library is used to learn a machine learning model. Lastly, the learnt machine learning model is used to determine whether the IoT network exists abnormal behaviors. The proposed framework is evaluated on ISOT Botnet dataset. [ABSTRACT FROM AUTHOR]

Edge computing technology solves the shortcomings of high latency, mobility and location awareness in remote cloud computing, but it also brings many security challenges to the AIoT. In view of the open and heterogeneous characteristics of edge network, a more secure edge computing intrusion detection method is studied in this paper. The main idea is to combine edge computing with AIoT to realize edge smart interconnection. This method optimizes the weight value in machine learning by increasing the screening and mitigation of cloud server training samples, so as to provide efficient and accurate edge intrusion detection behavior. The experimental results show that the proposed method can more effectively improve the detection accuracy and reduce the detection time. [ABSTRACT FROM AUTHOR]

In this paper, we describe a novel iterative procedure called SISTA to learn the underlying cost in optimal transport problems. SISTA is a hybrid between two classical methods, coordinate descent ("S"‐inkhorn) and proximal gradient descent ("ISTA"). It alternates between a phase of exact minimization over the transport potentials and a phase of proximal gradient descent over the parameters of the transport cost. We prove that this method converges linearly, and we illustrate on simulated examples that it is significantly faster than both coordinate descent and ISTA. We apply it to estimating a model of migration, which predicts the flow of migrants using country‐specific characteristics and pairwise measures of dissimilarity between countries. This application demonstrates the effectiveness of machine learning in quantitative social sciences. © 2022 Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

In the past years, multimedia content has improved in realism and plausibility owing to the development of deep learning techniques, particularly the generative adversarial networks and variational auto‐encoders. Though digital content, especially digital movies shot from a certain viewpoint gives a true representation of reality, yet the ubiquitous usage of content manipulation techniques casts doubt on its veracity. Deepfaking an AI based tampering technique, is able to map facial and acoustic features of a source person onto the target with an intention to make target say or enact the things that has not happened in real. Numerous approaches have been proposed in the literature for detection of image and video deepfakes. With technological advancement, researchers have also started to examine audio deepfakes and ways to detect them. As there is currently no comprehensive overview of audio deepfake generation and detection techniques, this paper aims to provide a survey of the relevant literature in this area. This survey paper intends to help research fraternity about the available audio generation and detection approaches for design of reliable detection models in future to classify fake and real audios. [ABSTRACT FROM AUTHOR]

Gesture recognition nowadays has grabbed the attention of researchers as they represent human behaviour in multiple practical ways. Amongst a variety of gestures available, hand gestures play an essential role in the field of human‐computer interaction when recognised efficiently in complex and dynamic environments. In this paper, we propose a dynamic hand gesture recognition system to recognise hand gestures appearing in different indoor and outdoor environments. Hand detection and tracking uses a two‐level system resulting in the formation of gesture trajectory in challenging conditions in which existing detection and tracking algorithms could not do so. A set of 45 features is provided as input to the various classification techniques. The redundancy problem has been reduced by selecting a set of optimum features using the analysis of variance method, which ranks the list of features. An incremental feature selection technique calculates recognition accuracy by selecting features according to rankings. This system provides an accuracy of 96.32% when used with machine learning and 97.5% when used with deep learning techniques. Recognition accuracy is calculated for various environments, including an extra hand, multiple persons in the video frame, and outdoor environment. All machine‐learning classifiers are combined using classifier combination to calculate the accuracy according to the majority‐voting rule. Based on the experimental results, it has been observed that deep learning provides better results compared to machine learning. [ABSTRACT FROM AUTHOR]

With the continuous development of intelligent refrigerators, users are having higher and higher requirements for smart management of refrigerator contents. When using traditional machine learning algorithms to deal with refrigerator ingredients classification, problems such as slow recognition speed and low accuracy would often arise. At the same time, the classification accuracy is easily affected by the location of the content. Therefore, this paper uses continuous asymmetric convolutions and depthwise separable convolutions to improve the original Inception model and builds a classification prediction network based on the improved Inception model. The steps to applying the said model is as follows: First, we put the Radio Frequency Identification (RFID) tag on the food in the refrigerator, and then we collect the antenna data RSSI received by each tag through the reader. Finally, the RSSI is preprocessed and entered into the classification network to determine the location of the label. The proposed classification network has the advantages of possessing a simple structure, easy expansion of network depth, and fewer training parameters. The experimental results show that compared with other machine learning algorithms and pure convolution networks, the lightweight network model based on the improved Inception structure demonstrates great superiority. Compared with the original Inception structure, the enhanced network model is more lightweight. The number of parameters is reduced by 50%, and the amount of float‐point operations is reduced by 34%. Meanwhile, the accuracy of the lightweight model has been improved by 0.6%. Thus the improved model has better prediction performance in the classification of refrigerator content. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Power line insulator defect identification usually suffers from complex backgrounds, small defect target sizes, and inconspicuous defect features. Traditional identification methods based on image processing, image analysis, and pattern classification have many limitations in solving the aforementioned problems. In recent decades, deep learning classification methods have gradually replaced traditional identification methods in the task of power line insulator defect identification. To accurately identify the locations of insulator defects, this paper proposes an insulator defect detection algorithm using an improved lightweight YOLOv4‐tiny network (ILYTN). First, the CBL (Conv‐BN‐LeakyReLU) modules of the backbone network are replaced with MobileViT blocks to enhance the feature extraction capability of the backbone network. Second, coordinate attention (CA) is introduced in the feature fusion part to improve the network's ability to focus on the location of defects. Finally, an EIOU (efficient intersection over union) loss function, instead of the original CIOU loss function, is used so that the convergence speed of the network can be improved. To verify the effectiveness of the proposed algorithm in this paper, the mViT‐yolo algorithm is compared with the mainstream Faster‐RCNN algorithm, SSD algorithm, YOLOv3 algorithm, and YOLOv4‐tiny algorithm. The experimental results show that the algorithm proposed in this paper outperforms all the above algorithms in terms of detection accuracy. Compared with the traditional YOLOv4‐tiny algorithm, the proposed algorithm increases the mean average precision (mAP) by 1.64%, the average precision (AP) of missing insulator defects by 0.32%, and the average precision (AP) of broken insulator defects by 4.96%. © 2023 The Authors. IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Critical care (CC) pharmacists have been contributing to patient outcomes, team effectiveness, education, research and quality improvement for approximately 50 years. Current CC specialists are evolving the practice, science and scholarship into new and exciting areas as described in the series of articles collected for a special series in this journal. To summarize past accomplishments and contemplate how next level achievements may develop, brainstorming by experienced CC specialists, researchers, educators, and scholars was done to establish a foundation for this paper and three of that group summarized it into an overview of the challenges of the past and opportunities that are shaping the future. A small group of CC pharmacists identified need and opportunity to improve patient care in a limited number of settings but subsequent CC pharmacists have expanded into numerous specialties and subspecialties. Comprehensive medication management of CC patients and survivors of their critical illness is now a standard, but delivery may be influenced by new technology and equipment. Improved quality of care and outcome measures are being developed and measured. The imperative to move practice forward and adopt new practices while maintaining a core set of guideline‐based practices may be facilitated by technology such as wearable devices, personalized medicine, machine learning or artificial intelligence. However, these new tools may create new obstacles. Similar changes in education and expansion into administrative roles afford new opportunities and challenges. CC pharmacists have created a solid foundation, but continued growth in number and expansion of roles requires the next generation to continue to push ahead and continue to demonstrate value in key areas. [ABSTRACT FROM AUTHOR]

In this paper, a wearable OLED in‐cell self‐capacitive sensor using machine learning algorithm for water‐proofing is proposed. This paper also shows the experiment and the test result. The result shows that the success rate of water‐proofing on bezel can be largely improved (from 30.7% to 77.1%) by machine learning method on the wearable device with Novatek TDDI NT38350. [ABSTRACT FROM AUTHOR]

Summary: Gesture recognition is the foremost need in building intelligent human‐computer interaction systems to solve many day‐to‐day problems and simplify human life in this digital world. The traditional machine learning (ML) algorithm tried to capture specific handcrafted features, failed miserably in some real‐world environments. Deep learning (DL) techniques have become a sensation among researchers in recent years, making the traditional ML approaches quite obsolete. However, existing reviews consider only a few datasets on which DL algorithm has been applied, and the categorization of the DL algorithms is vague in their review. This study provides the precise categorization of DL algorithms and considers around 15 gesture datasets on which these techniques have been applied. This study also provides a brief overview of the numerous challenging dataset available among the research community and insight into various challenges and limitations of a DL algorithm in vision‐based dynamic gesture recognition. [ABSTRACT FROM AUTHOR]

A challenge unique to classification model development is imbalanced data. In a binary classification problem, class imbalance occurs when one class, the minority group, contains significantly fewer samples than the other class, the majority group. In imbalanced data, the minority class is often the class of interest (e.g., patients with disease). However, when training a classifier on imbalanced data, the model will exhibit bias towards the majority class and, in extreme cases, may ignore the minority class completely. A common strategy for addressing class imbalance is data augmentation. However, traditional data augmentation methods are associated with overfitting, where the model is fit to the noise in the data. In this tutorial we introduce an advanced method for data augmentation: generative adversarial networks (GANs). The advantages of GANs over traditional data augmentation methods are illustrated using the Breast Cancer Wisconsin study. To promote the adoption of GANs for data augmentation, we present an end‐to‐end pipeline that encompasses the complete life cycle of a machine learning project along with alternatives and good practices both in the paper and in a separate video. Our code, data, full results and video tutorial are publicly available in the paper's GitHub repository (https://github.com/yuxiaohuang/research/tree/master/gwu/accepted/sam_2021). [ABSTRACT FROM AUTHOR]

With the rapid development of re‐electrification, traditional load forecasting faces a significant increase of influencing factors. Existing literature focuses on examining the influencing factors related to load profiles in order to improve the prediction accuracy. However, a large number of redundant features may lead to the overfitting of the forecasting engine. To enhance the performance of extreme learning machine (ELM) under massive data scale, this paper presents a kernel extreme learning machine (KELM) based method which can be used for short‐term load prediction. First, a feature dimensionality reduction is performed using a kernelized principal component analysis, which aims to eliminate redundant input vectors. Then, the hyperparameters of KELM are optimized to improve the prediction accuracy and generalization. Case studies based on a province‐level power system in China demonstrate that the presented method can significantly improve the accuracy of load forecasting by 3.14% in contrast to traditional ELM. [ABSTRACT FROM AUTHOR]

In order to eliminate the influence of scene illumination on the evaluation of the color difference of dyed fabrics, this paper proposes a dyed fabric illumination correction algorithm based on the extreme learning machine (ELM) with grey wolf optimizer (GWO)‐optimized ant lion optimizer (ALO). Firstly, the Grey Edge framework is used to extract the features of the dyed fabric image as the input vector. Then, to improve the optimization ability of the ALO algorithm, the GWO algorithm is used to provide a set of optimized initial populations to the ALO algorithm, and then the improved ALO algorithm is used to optimize the parameters of the ELM. Finally, the proposed GWO‐ALO‐ELM algorithm is used to correct the illumination of the dyed fabric, and restore the graphics to the effect display under standard illumination through the diagonal reduction model. Compared with the experimental results of GWO‐ELM, ALO‐ELM, backpropagation (BP), ELM, random vector function link (RVFL), and other algorithms, it can be seen that the GWO‐ALO‐ELM algorithm proposed in this paper has good predictive value and quasi‐bias effect, and good stability. [ABSTRACT FROM AUTHOR]

Background: Digital‐first assessments leverage the affordances of technology in all elements of the assessment process: from design and development to score reporting and evaluation to create test taker‐centric assessments. Objectives: The goal of this paper is to describe the engineering, machine learning, and psychometric processes and technologies of a test security framework (part of a larger ecosystem; Burstein et al., 2021) that can be used to create systems that protect the integrity of test scores. Methods: We use the Duolingo English Test to exemplify the processes and technologies that are presented. This includes methods for actively detecting and deterring malicious behaviour (e.g., a custom desktop app). It also includes methods for passively detecting and deterring malicious behaviour (e.g., a large item bank created through automatic generation methods). We describe the certification process that each test administration undergoes, which includes both automated and human review. Additionally, we describe our quality assurance dashboard which leverages psychometric data mining techniques to monitor test quality and inform decisions about item pool maintenance. Results and Conclusions: As assessment developers transition to online delivery and to a design approach that places the test taker at the centre, it becomes increasingly important to take advantage of the tools and methodological advances in different fields (e.g., engineering, machine learning, psychometrics). These tools and methods are essential to maintaining the security of assessments so that the score reliability is sustained and the interpretations and uses of test scores remain valid. Lay Description: What is known about this topic?: As more and more testing programmes transition to test taker‐centric administrations, effective measures to prevent cheating and protect content are critical to ensure the validity and integrity of scores.Two of the most common forms of cheating in online testing are (a) having someone other than the person who has registered take the test, and (b) stealing content and providing it to others to assist them in achieving a higher score. What does this paper add?: In designing a test taker‐centric digital‐first assessment, a test security framework must inform decisions from end‐to‐end (i.e., registration, onboarding, communications regarding test taker behaviours, test preparation and practice, test administration, and post‐administrative activities including scoring).Security is safeguarded through active and passive design methods; active methods include having test takers attest that they will follow the rules governing testing and informing them that they will be videoed during testing; passive methods include a computer adaptive design that limits item exposure and test overlap rates, development of a large item pool using automated item generation, and applying artificial intelligence to review test administration videos to flag unauthorized behaviours for human review. Implications: With more educational and assessment programmes transitioning to online digital models, the paper presents a comprehensive review of security issues and identifies an integrated approach for preventing cheating and other unauthorized behaviours. [ABSTRACT FROM AUTHOR]

Commercial buildings are consuming an increasing amount of energy, and accurate load demand forecasting is critical for the reliable operation of power systems and the efficient use of resources. Therefore, in this paper, a short‐term commercial load forecasting model based on tunicate swarm algorithm (TSA) combined with an extreme learning machine (ELM) under peak‐valley features is proposed as a research case for a shopping mall in Romania. This paper's overall structure is divided into two steps. In the first step, the 24‐h day is divided into six periods by analyzing the daily load characteristics of the training set, and the peak and valley loads are obtained. The ELM optimized by TSA (TSA‐ELM) algorithm is then used to forecast the peak and valley values of the test set one day ahead. In the second step, the actual load, peak, and valley for the previous week of historical load are chosen using the maximum information coefficient (MIC). Following that, the MIC ≥ 0.8 features are added to the TSA‐ELM to achieve short‐term commercial electricity load forecasting. The results show that the PV (Peak & Valley)‐TSA‐ELM model proposed in this paper has higher prediction accuracy compared with other models. Taking ELM as an example, compared with the traditional ELM, the mean absolute error, root mean square error, and mean absolute percentage error of PV‐TSA‐ELM are reduced by 20.59%, 20.13%, and 19.19% on average in the three commercial data sets. The proposed model is validated with an industrial data set, and ideal results are obtained, which verifies the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

The article discusses the importance of localisation in various applications such as healthcare, smart cities, and transportation. It highlights the challenges faced in achieving accurate and timely position data, particularly in indoor settings. The integration of artificial intelligence (AI) and machine learning techniques is seen as a way to enhance indoor wireless localisation effectiveness. The article presents four papers that explore different methods and algorithms to improve localisation accuracy and efficiency in sensor networks. The authors encourage further research and contributions to address the evolving challenges in this field. [Extracted from the article]

And of course we thank the General Chair Gerik Scheuermann, and Vice Chairs Dirk Zeckzer, Olaf Kolditz, and Mario Hlawitschka, for their efforts in creating the full conference, a highly successful event for researchers, authors, students, all interested and the community at large. We thank the chairs of the other conference tracks for their help in making EuroVis 2023 such a successful event: Short Paper chairs Thomas Hoellt, Wolfgang Aigner, and Bei Wang; STAR chairs Stefan Bruckner, Renata Raidou, and Cagatay Turkay; the Posters Chairs Simone Lenti, Michael Krone, and Christina Gillmann; the Panels and Tutorials Chairs Hans-Jörg Schulz and Ingrid Hotz, the Workshop Chairs Karsten Rink, Jürgen Bernard, and all the chairs of the co-located workshops; the Student Volunteer Chair Felix Raith, and the Dirk Bartz Prize Chairs Renata Raidou and Torsten Kuhlen. We also thank very much the Program Chair Christian Heine for working on the program, the Online Chair Daniel Wiegreffe for organizing the online and video material of the conference, and the Communication Chair Vanessa Kretzschmar for announcing and making aware of the conference in web and social media. [Extracted from the article]

In the context of Heterogeneous Wireless Networks (HWN), achieving the best connectivity is crucial for users. With the availability of multiple Radio Access Technologies (RATs), users are constantly looking to be "Always Best Connected" (ABC) by connecting to the best possible RAT. This challenge is also important in Next‐Generation Networks (NGN), where researchers are proposing models and algorithms to make the ABC paradigm a reality. One such challenge is the network selection problem, which involves the automatic and transparent selection of the best RAT at a given time. Many papers in this field have used Multi‐Attribute Decision‐Making (MADM) methods, which have been implemented with various objectives such as increasing quality of service (QoS), reducing energy consumption and costs etc. This paper proposes a modified machine learning algorithm, specifically an adapted K‐means algorithm, to address this challenge. The results show that this proposal outperforms legacy MADM methods in terms of latency, jitter, packet loss, and data rate. So, the paper presents a new approach to network selection in HWN and NGN, and the results suggest that it could be a promising solution to this important challenge. [ABSTRACT FROM AUTHOR]

There are hundreds of prognostic models for ovarian cancer. These genes are based on different gene classes, and there are many ways to construct the models. Therefore, this paper aims to build the most stable prognostic evaluation system known to date through 101 machine learning strategies. We combined 101 algorithm combinations with 10 machine learning algorithms to create antigen presentation‐associated genetic markers (AIDPS) with outstanding precision and steady performance. The inclusive set of algorithms comprises the elastic network (Enet), Ridge, stepwise Cox, Lasso, generalized enhanced regression model (GBM), random survival forest (RSF), supervised principal component (SuperPC), Cox partial least squares regression (plsRcox), survival support vector machine (Survival‐SVM). Then, in the train cohort, the prediction model was fitted using a leave‐one cross‐validation (LOOCV) technique, which involved 101 different possible combinations of prognostic genes. Seven validation data sets (GSE26193, GSE26712, GSE30161, GSE63885, GSE9891, GSE140082 and ICGC_OV_AU) were compared and analysed, and the C‐index was calculated. Finally, we collected 32 published ovarian cancer prognostic models (including mRNA and lncRNA). All data sets and prognostic models were subjected to a univariate Cox regression analysis, and the C‐index was calculated to demonstrate that the antigen presentation process should be the core criterion for evaluating ovarian cancer prognosis. In a univariate Cox regression analysis, 22 prognostic genes were identified based on the expression profiles of 283 genes involved in antigen presentation and the intersection of genes (p < 0.05). AIDPS were developed by our machine learning‐based integration method, which was applied to these 22 genes. One hundred and one prediction models are fitted using the LOOCV framework, and the C‐index is calculated for each model across all validation sets. Interestingly, RSF + Lasso was the best model overall since it had the greatest average C‐index and the highest C‐index of any combination of models tested on the validated data sets. In comparing external cohorts, we found that the C‐index correlated AIDPS method using the RSF + Lasso method in 101 prediction models was in contrast to other features. Notably, AIDPS outperformed the vast majority of models across all data sets. Antigen‐presenting anti‐tumour immune pathways can be used as a representative gene set of ovarian cancer to track the prognosis of patients with cancer. The antigen‐presenting model obtained by the RSF + Lasso method has the best C‐INDEX, which plays a key role in developing antigen‐presenting targeted drugs in ovarian cancer and improving the treatment outcome of patients. [ABSTRACT FROM AUTHOR]

Nowadays, the development of Artificial Intelligence of Things (AIoT) is advancing rapidly, and intelligent devices are increasingly exposed to more security risks on the network. Deep learning‐based intrusion detection is an effective security defence approach. Federated learning (FL) is capable of enabling deep learning models to be trained on local clients without uploading their data to a central server. This paper proposes a novel federated learning aggregation algorithm called fed‐dynamic gravitational search algorithm (Fed‐DGSA), which incorporates the GSA algorithm to optimize the weight updating process of FL local models. During the updating process, the decay rate of the gravity coefficient is optimized and random perturbations and dynamic weights are introduced to ensure a more stable and efficient FL aggregation process. The experimental results show that the detection accuracy of Fed‐DGSA has reached about 97.8%, and it is demonstrated that the model trained using Fed‐DGSA achieves higher accuracy compared to Fed‐Avg. [ABSTRACT FROM AUTHOR]

This paper aims to update our understanding of the carbon cycle in the Himalayas, the most intense collisional orogeny globally, by providing new insight into its impact on Cenozoic climate cooling through the use of isotopic variations in both organic and inorganic carbon and an isotopic mass balance model. Our results from 20 selected hot springs show that the relative contributions of dissolved carbon from the mantle, metamorphic decarbonization, aqueous dissolution, and soil organic matter are approximately 2%, 82%, 6%, and 10%, respectively. Approximately 87% ± 5% of CO2 generated in the deep crust precipitates as calcite, while approximately 5.5% ± 1% of this carbon is converted to biomass through microbial chemosynthesis at depths less than 2 km. Our random forests approach yielded a metamorphic carbon flux from the entire Himalayan orogenic belt of approximately 2.7 ∼ 4.5 × 1012 mol/yr. The minor CO2 released into the atmosphere (2.5 ∼ 4.2 × 1011 mol/yr) is comparable to the carbon consumption driven by Himalayan weathering. This paper provides new insights into deep carbon cycling, notably that approximately 93% of deeply sourced carbon is trapped in the shallow crust, rendering orogenic processes carbon neutral and possibly acting as one of the major triggers of long‐term climate cooling in the Cenozoic. Plain Language Summary: Large‐scale deep metamorphic decarbonization and CO2 release into the atmosphere during continental collision orogenesis worldwide have had significant impacts on Cenozoic global climate change. However, the carbon sources and sinks and the mechanisms underlying their impacts on climate change are not fully understood. This paper reports the chemistry of aqueous solutions, carbon isotopic compositions of dissolved inorganic carbon (DIC) and dissolved organic carbon (DOC), and helium and carbon isotopic compositions of free gases from hot springs in southern Tibet. The carbon isotope fractionation model between gas and aqueous solutions revealed that the carbon released from depth underwent six different stages. Based on the random forests machine learning algorithm, we estimated the metamorphic carbon flux across the Himalayan orogenic belt. Furthermore, only a small fraction (7%) of deep carbon is eventually released into the atmosphere, and this volume is the same magnitude as the amount of carbon absorbed by silicate weathering on the Tibetan Plateau. This paper emphasizes that the carbon sequestration process in the upper crust may have resulted in nearly carbon‐neutral geological bodies in the Himalayan orogenic belt, thus playing a critical role in Cenozoic climate cooling. Key Points: Approximately 87% of deeply sourced carbon precipitates as calcite, while approximately 5.5% is sequestered as biomass in the shallow crustThe carbon flux across the Himalayan orogenic belt was estimated by the random forests approachCrustal thickening has attenuated long‐term deep carbon emissions from the Himalayas [ABSTRACT FROM AUTHOR]

Background: Driven by the ongoing need to provide high‐quality learning and teaching, universities recently have shown an increased interest in using learning analytics (LA) for improving learning design (LD). However, the evidence of such improvements is scarce, and the maturity of such research is unclear. Objectives: This study is aimed to evaluate the maturity of research discussing LA‐driven LD improvements in higher education. Methods: The systematic review analyses 49 empirical papers, assesses their quality and suggests further research directions. The review elaborates on methodological (research questions, strategy and methods, LA‐LD integration theoretical backgrounds) and substantial (LA‐driven LD improvements, types of data used, LA software development) features of the papers. Results and Conclusions: The findings demonstrated the lack of theoretical alignment between LA and LD, with research tending towards user experience studies. The most frequently used research strategy was a case study; experiments were very rare. Researchers predominantly used parsing for collecting data and AI methods for analysing it; mostly used data types related to registering learners' engagement with learning activities as well as resources and tools provided in digital learning environments. Takeaways: The research area discussing LA‐driven LD improvements still has a way to go before attaining the level of full maturity. Only a third of the papers reported actual LA‐driven LD improvements; moreover, only three papers measured their effectiveness. The presented LA software was mostly at the beta or implementation stages and did not assess the impact of using this software. Lay Description: What is already known about this topic: Universities show an increased interest in using LA for improving LD.The evidence of such improvements being efficient is scarce.Learning analytics is weakly grounded in learning and teaching. What this paper adds: LA‐LD research presented in the reviewed papers cannot yet be considered fully mature.Almost half of the research was carried out using a case study approach, intrinsically challenging in terms of replication and validity. As few as three out of the reviewed studies applied an experimental approach, capable of stating the cause–effect relationship between LA and LD.All the studied papers mentioned improvements in LD, but only around a third of them reported actual improvements, another one‐third suggested potential improvements, and the rest did not come down to describing any.The LA software presented in the papers was mostly at the testing or implementation stages, and the impact of implemented software on LD has yet to be evaluated. Implications for practice and/or policy: Future LA‐LD research to become more mature may well elaborate on theoretical footing, contribute to the cause–effect relationship between LA and LD utilising experimental research design, ensure sufficient sample size.Practitioners' efforts should be directed to operationalising LD for efficient measurements, addressing pedagogical challenges when applying LA, and assessing LA‐driven improvements introduced into LD. [ABSTRACT FROM AUTHOR]

This paper proposes a deep reinforcement learning algorithm to achieve complete coverage path planning for deep‐sea mining vehicle clusters. First, the mining vehicles and the deep‐sea mining environment are modeled. Then, this paper implements a series of algorithm designs and optimizations based on Deep Q Networks (DQN). The map fusion mechanism can integrate the grid matrix data from multiple mining vehicles to get the state matrix of the complete environment. In this paper, a preprocessing method for the state matrix is also designed to provide suitable training data for the neural network. The reward function and action selection mechanism of the algorithm are also optimized according to the requirements of cluster cooperative operation. Furthermore, the algorithm uses distance constraints to prevent the entanglement of underwater hoses. To improve the training efficiency of the neural network, the algorithm filters and extracts training samples for training through the sample quality score. Considering the requirement of cluster complete coverage mission, this paper introduces Long Short‐Term Memory (LSTM) based on the neural network to achieve a better training effect. After completing the above optimization and design, the algorithm proposed in this paper is verified through simulation experiments. [ABSTRACT FROM AUTHOR]

Copyright of Methods in Ecology & Evolution is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We propose an autoregressive weighted network (ARWNet) time series forecasting model inspired by the idea of ensemble learning. The model adopts the classical autoregressive analysis to optimize weak learners. Meanwhile, the combined weight optimization method is used to construct an efficient, strong learner. With these methodological foundations, the scalability of the framework is greatly enhanced by the possibility of experimenting with other learners to assist in decision‐making. Machine learning can provide great utility and acceptable cost in the prediction process of electricity transformers. Over the years, many research papers on time series prediction have been reported. This work will focus on the analysis using the potential properties in the series: long‐term, continuity, periodicity, and delay. In our experiments, the ETT‐small dataset is used to compare the prediction accuracy of ARWNet and other mainstream models. All results suggest that the proposed ARWNet model demonstrates strong generalization ability and high predicting accuracy with delay characteristics, which outperform current popular time‐series prediction methods. [ABSTRACT FROM AUTHOR]

As electrochemical research undergoes rapid technological progression, the acquisition of substantial amounts of electrochemical impedance spectra (EIS) becomes increasingly feasible. Yet, this advancement introduces intricate challenges in data processing, automation, and interpretation. This paper delves into the sufficiency of unsupervised machine learning (ML) and in particular dimensionality reduction methods in decoding EIS complexities, examining its strengths, limitations, and potential pathways for optimization. As we navigated the intricacies of non‐linear dimensionality reduction, spotlighting t‐distributed stochastic neighbor embedding (t‐SNE) and uniform manifold approximation and projection (UMAP) algorithms, a pattern emerged: these techniques excel at categorizing divergent impedance spectra but show limitations when faced with analogous circuit configurations, especially those substituting a capacitor with a constant phase element. This observation not only underscores a limitation but also accentuates that unsupervised ML approaches, alone, may not fully unravel the nuances of EIS spectra. In the concluding section of our manuscript, we discuss the implications of this finding from a practical standpoint, particularly for electrochemists seeking to apply these methods in their work. [ABSTRACT FROM AUTHOR]

This paper aims to study the phased influencing factors of renminbi (RMB) exchange rate (CNY against USD) and investigate the predictability of the factors selected by multimodel. We first take the time points when China's main exchange reform policies are launched as the demarcation points and divide the entire sample from July 2005 to December 2020 into three periods. Then, we select the potential predictors using several sources, including all factors (without any selection), the factors selected by each of the five commonly used machine learning methods, the significantly correlated factors selected by traditional regression analysis method, and multimodel‐driven factors. Finally, we predict the exchange rate based on the above selected factors and compare the prediction results. The research results show that the main influencing factors are different in different periods, and the influence of phase events cannot be ignored. Even if their influence on the exchange rate has decreased as a result of the "811" exchange rate reform, the money supply and foreign exchange reserves continue to be the primary drivers of RMB exchange rates during the whole period of the sample. Additionally, RMB exchange rate forward is a robust influencing factor in all periods. By comparing the forecast errors, we find that the prediction accuracy of the factors selected based on multimodel is higher than that of the factors selected based on a single method or the tradition method. The findings of this paper provide the following insights for exchange rate managers: In exchange rate risk management, it is important to pay attention to the impact of macroeconomic factors such as foreign exchange reserves and the impact of staged events, and market expectations of exchange rates are equally important. At the technical level, it is recommended to improve the forecasting accuracy by forecasting exchange rates based on common factors selected by multiple better machine learning methods simultaneously rather than those selected by a single method. [ABSTRACT FROM AUTHOR]

Visual surveillance systems have been playing an important role in monitoring and managing at public areas. However, the computational complexity of video compression in these applications is still a great challenge. To meet practical requirements, the authors propose in this paper a low‐complexity surveillance video coding solution in which the most recent Versatile Video Coding (VVC) standard is improved with a novel learning adaptive motion search algorithm. The proposed algorithm is designed based on the temporal motion and spatial texture characteristics of surveillance videos. First, the authors study and define a list of spatial and temporal features which indicates the motion and texture characteristics of surveillance video. These features are used together with a machine learning algorithm to appropriately assign a search range for the VVC motion search. Second, to reduce search points, the authors propose an adaptive Test Zone (TZ) search in which TZ steps are early terminated following the variation of spatial–temporal features. Performance evaluation conducted for a rich set of surveillance videos and relevant benchmarks have shown the superiority of the proposed method, notably with around 33% of encoding time saving when compared with the state‐of‐the art VVC solution and relevant benchmarks while asking for negligible compression loss. [ABSTRACT FROM AUTHOR]

Deep learning is gaining importance due to its wide range of applications. Many researchers have utilized deep learning (DL) models for the automated diagnosis of cancer patients. This paper provides a systematic review of DL models for automated diagnosis of cancer patients. Initially, various DL models for cancer diagnosis are presented. Five major categories of cancers such as breast, lung, liver, brain and cervical cancer are considered. As these categories of cancers have a very high percentage of occurrences with high mortality rate. The comparative analysis of different types of DL models is drawn for the diagnosis of cancer at early stages by considering the latest research articles from 2016 to 2022. After comprehensive comparative analysis, it is found that most of the researchers achieved appreciable accuracy with implementation of the convolutional neural network model. These utilized the pretrained models for automated diagnosis of cancer patients. Various shortcomings with the existing DL‐based automated cancer diagnosis models are also been presented. Finally, future directions are discussed to facilitate further research for automated diagnosis of cancer patients. [ABSTRACT FROM AUTHOR]

Summary: A difficult problem in the service‐oriented computing paradigm is improving task scheduler policy or resource provisioning.In order to increase the performance of cloud applications, this article primarily focuses on tasks for resource mapping policy optimization. With the aim of reducing makespan and execution overhead and increasing the average resource utilization, we suggested an efficient independent task scheduler employing supervised neural networks in this paper. The suggested ANN‐based scheduler uses the status of the cloud environment and incoming tasks as inputs to determine the optimal computing resource for a given assignment as a result that assembles our goal. We proposed a novel algorithm in this paper that uses a hybrid methodology based on a swarm intelligence algorithm (PSO) in combination with a machine learning technique (ANN). PSO is used to prepare the train and test dataset for the neural network. Results clearly state that suggested work achieves significant improvement to considered algorithms in makespan (45%–55%), average VM utilization (15%–20%), and execution overhead(20%–30%). [ABSTRACT FROM AUTHOR]

Correct identification of tumor in brain images is critical for treatment. In the medical domain, class distributions of recorded data could differ with locations and require high levels of privacy while collaboratively training the deep learning (DL) models for classifications. The main aim of this paper is to propose a privacy‐preserving collaborative model for the classification of brain tumor in heterogeneously distributed magnetic resonance imaging (MRI) images. In this paper, initially, an open‐source dataset has been acquired and analyzed as per the required competencies. The acquired dataset has four types of MRI images: pituitary tumor, meningioma tumor, glioma tumor, and no tumor. First, the acquired dataset was analyzed using DL and transfer learning algorithms. By applying implementations of basic algorithms, better algorithms were identified for further implementations in a federated learning ecosystem. DenseNet201‐based transfer learning was identified as a better neural network and further utilized for collaborative transfer learning implementations. Here, the paper also focused on developing a suitable system for a heterogeneous distributed tumor database. Heterogeneous data were converted from the available data by applying nonidentical data distribution. The study discovered that the federated DL models, involving multiple clients, exhibited superior performance compared to conventional pretrained models. The proposed framework possesses distinctive characteristics that distinguish it from existing classification methods for brain tumor identification, particularly in terms of ensuring data privacy for edge devices with limited resources. Due to these additional features, the framework stands as the optimal alternative solution for early diagnosis of brain tumor. [ABSTRACT FROM AUTHOR]

The aptness of machine learning (ML) to learn from large datasets, discover trends, and make predictions has demonstrated its potential to metamorphose the medical field. Medical data analysis with ML algorithms can improve patient outcomes in terms of both treatment and diagnosis. This paper investigates the numerous possibilities of ML in the medical industries, including radiology, pathology, genomics, and clinical decision‐making. It also goes over the benefits and drawbacks of ML in various sectors as well as the limitations that come with its application. It illustrates the potential advantages of ML, such as better accuracy and efficiency in diagnosis and individualized treatment programs, through a review of previous studies. Lastly, it provides perspectives on prospective advancements and prospects for the discipline. This study also intends to investigate the applications of deep learning (DL) in the medical field. DL algorithms have performed exceptionally satisfactorily in several healthcare‐related fields. The main conclusions of the study are summarized, and their ramifications for the healthcare sector are discussed in this paper's conclusion. This paper intends to contribute to a greater understanding of the prevailing state of the discipline and the possibility for future developments by emphasizing the prospects of these methodologies to alter medical study and clinical practice. [ABSTRACT FROM AUTHOR]

Spectral data describing product samples are typically composed of a large number of noisy and irrelevant wavelengths that tends to undermine the performance of multivariate predictive techniques. This paper proposes a two‐phase framework that integrates a preselection wavelength step oriented by wavelength clustering to a wrapper‐based strategy. The first phase performs a pruning process in the data that removes the less informative wavelengths relying on the spectral clustering, a technique deemed suitable to the Fourier transform infrared (FTIR) spectroscopy and near‐infrared (NIR) spectroscopy data at hand. The preselected wavelengths undergo a second phase of selection efforts based on the combination of different wavelength importance indices (i.e., Bhattacharyya distance, Chi‐square, ReliefF, and Gini) and classification techniques (i.e., support vector machine, k‐nearest neighbors, and random forest). When applied to 11 FTIR datasets from different domains, the recommended combination of importance index and classifier increased the average accuracy by 6.37% (from 0.863 to 0.918), while retaining average 3.84% of the original spectra. The framework also improved the selection process regarding computational time. This paper introduces a two‐phase framework merging wavelength preselection through clustering and a wrapper strategy. Initial spectral clustering eliminates less informative wavelengths. Subsequently, diverse wavelength importance indices and classification methods are integrated. Applied to 11 spectral datasets, the proposed combination (spectral clustering [SC]‐random forest [RF]+Gini [GI]) enhances average accuracy by 6.37%, retaining 3.84% of the original spectra, and reduces computational time. [ABSTRACT FROM AUTHOR]

XGBoost is the optimization of gradient boosting with the best overall performance among machine learning algorithms. By introducing a regularization term into the loss function of gradient boosting, XGBoost can effectively limit the complexity of the model, improve the generalization ability, and solve the overfitting problem. In this paper, XGBoost is first introduced into modeling radio‐frequency (RF) power amplifiers (PA) under different temperatures. Furthermore, the modeling effect of XGBoost is mainly dependent on hyperparameters. As traditional grid search is time‐consuming and labor‐intensive, this paper combines particle swarm optimization (PSO) with XGBoost for searching hyperparameters. The experimental results show that XGBoost can effectively suppress the overfitting problem in gradient boosting while modeling RF PAs in different ambient temperatures. In addition, compared to classic machine learning algorithms, including support vector regression (SVR), gradient boosting, and XGBoost, the proposed PSO‐XGBoost can increase the modeling accuracy by one order of magnitude or more while also increasing the modeling speed by more than one magnitude or more. The PSO‐XGBoost model proposed in this paper can be introduced into modeling other microwave/RF devices and circuits to improve modeling accuracy and reduce modeling time. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate the utilization of artificial neural networks (ANNs) in learning models that address the nonlinear anisotropic flow and hysteresis retention behavior of deformable porous materials. Herein, the micro‐geometries of various networks of porous Bentheimer Sandstones subjected to several degrees of strain from the literature are considered. For the generation of the database required for the training, validation, and testing of the machine learning (ML) models, single‐phase and biphasic lattice Boltzmann (LB) simulations are performed. The anisotropic nature of the intrinsic permeability is investigated for the single‐phase LB simulations. Thereafter, the database contains the computed average fluid velocities versus the pressure gradients. In this database, the range of applied fluid pressure gradients includes Darcy as well as non‐Darcy flows. The generated output from the single‐phase flow simulations is implemented in a feed‐forward neural network, representing a path‐independent informed graph‐based model. Concerning the two‐phase LB simulations, the Shan‐Chen multiphase LB model is used to generate the retention curves of the cyclic drying/wetting processes in the deformed porous networks. Consequently, two different ML path‐dependent approaches, that is, 1D convolutional neural network and the recurrent neural network, are used to model the biphasic flow through the deformable porous materials. A comparison in terms of accuracy and speed of training between the two approaches is presented. Conclusively, the outcomes of the papers show the capability of the ML models in representing constitutive relations for permeability and hysteretic retention curves accurately and efficiently. [ABSTRACT FROM AUTHOR]

Tsunami simulations require powerful computational resources to be performed efficiently. Although the modern graphics processing units (GPUs) allow the acceleration of this kind of simulations, they can still last many minutes or even hours for simulations which have to deal with very high spatial resolutions or simulation times. In this paper, we propose a method to predict the alert or inundation level of a tsunami generated by an earthquake using deep learning methods. In particular, we train multilayer perceptron (MLP) neural networks for predicting the alert level due to a tsunami at given coastal locations. Ensemble methods are used to improve the predictions of the neural networks. Tsunamis caused by ruptures of several fault segments at different time instants, application to real events, probabilistic forecasting and comparison with other machine learning algorithms are also addressed. Results on realistic scenarios confirm that good accuracies are obtained. The inference times of the trained networks and ensembles are also very low, lasting less than one second to predict the results of thousands of simulations. The proposed method could be used in a tsunami early warning system along with the application of scaling laws. Plain Language Summary: In tsunami early warning systems (TEWS) it is crucial to perform fast predictions of the risk of a tsunami in coastal areas in order to take appropriate measures before the arrival of the tsunami. Currently, tsunami simulations may take many minutes or even hours despite using modern computational resources. In this work we propose a method based on deep learning techniques to predict the alert level of a tsunami generated by an earthquake at given coastal locations in a fraction of a second. This method could be used in TEWS along with techniques to estimate the values of some parameters of the earthquake. Application to real events and probabilistic predictions are also addressed. Key Points: A deep learning method to predict different tsunami alert levels is proposedTsunamis caused by the rupture of multiple fault segments at different time instants are supportedApplication to real events with probabilistic predictions are addressed [ABSTRACT FROM AUTHOR]

In this paper, we propose the usage of an ensemble learning approach for predicting total electron content (TEC). The training data set spans from 2007 to 2016, while the testing data set is set to the year 2017. The model inputs in our study included Solar radio flux (F107), Solar Wind plasma speed, By, Bz, Dst, Ap, AE, day of year, universal time, 30‐day and 90‐day TEC averages. Specifically, eXtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree, and Decision Tree were utilized for 1‐hr TEC prediction at high‐ (80°W, 80°N), mid‐ (80°W, 40°N), and low‐ latitudes (80°W, 10°N). Results indicate that all three models performed well in predicting TEC, with a mean error of only approximately 0.6 TECU at high‐ and mid‐ latitudes and 1.13 TECU at low latitudes. At the same time, we compared the model with 1‐day Beijing University of Aeronautics and Astronautics model during the period of magnetic storm from 25 August 2018 to 27 August 2018 and a quiet period from 13 December 2018 to 15 December 2018. In the magnetic storm period, Our model showed an average reduction of 1.83 TECU compared to BUAA model. During the quiet period, XGBoost exhibit an average error that is 1.14 TECU lower than that of BUAA model. Moreover, TEC prediction over the region between the 20°N–45°N and 70°E−120°E during geomagnetic storm has an error of 2.74 TECU, showing the stability and superiority of XGBoost. Overall, the ensemble learning approach exhibits its advantage in predicting TEC. Plain Language Summary: Due to the impact of the ionosphere on the propagation of radio waves and its significant influence on global navigation satellite systems, we have conducted modeling of the ionospheric total electron content (TEC), which describes the morphology and structure of the ionosphere. We propose the use of eXtreme Gradient Boosting (XGBoost), Gradient Boosting Decision Tree, and Decision Tree to predict TEC in different geographical latitudes. We also evaluate the best prediction time of the XGBoost model in a day. Additionally, the XGBoost model was tested during a geomagnetic storm, and TEC prediction over the region between 20°N and 45°N and 70°E−120°E showed the average error of 2.74 TECU, indicating its stability and superiority. Key Points: Three ensemble learning models are employed to predict total electron content (TEC) in various latitudes using data spanning a solar cycleeXtreme Gradient Boosting model has less predicted errors than Gradient Boosting Decision Tree and Decision Tree models, and the previous TEC history dominants the predicted TEC valuesThe RMSE increases with the predicted time advance, and the average relative error is the minimum in the mid‐latitude [ABSTRACT FROM AUTHOR]

Cable trees are primarily employed in industrial products to facilitate energy transfer and information exchange among various components. When utilizing machines for assembly, it is essential to convert the wiring plan into a sequence of cable insertion operations executed by the machine under various constraints. This poses a combinatorial optimization problem. In this domain, constraint programming (CP) solvers often exhibit outstanding performance by leveraging their robust problem‐modelling capabilities, excellent scalability, and precise solving capabilities. However, CP solvers may achieve various performances for different problem instances. Selecting the most suitable CP solver for each problem instance is crucial. This paper introduces an automatic selection algorithm for CP solvers to solve the cable tree wiring problem (CTW). Firstly, a scoring system is used to conduct an in‐depth analysis and compare four well‐known CP solvers: CPLEX, Chuffed, OR‐Tools, and Gurobi. The results indicate that OR‐Tools and CPLEX outperform other solvers in performance. Moreover, these two solvers exhibit complementary advantages in quickly finding optimal and feasible solutions within specified time limits. Therefore, CP and machine learning are ingeniously integrated, harnessing their complementary advantages. 4240 instances covering various scenarios are randomly generated to form the problem space. This method incorporates decision trees, random forests, K‐nearest neighbours, and naive Bayes, utilizing these four machine learning techniques. The proposed method can achieve better results than traditional single CP solvers. Among all the evaluated machining learning techniques, the automatic solver selection methods based on decision trees and random forests can achieve accuracy rates of 91.29% and 84.15%, respectively. [ABSTRACT FROM AUTHOR]

Purpose: Deep learning-based auto-segmentation algorithms can improve clinical workflow by defining accurate regions of interest while reducing manual labor.Over the past decade,convolutional neural networks (CNNs) have become prominent in medical image segmentation applications. However, CNNs have limitations in learning long-range spatial dependencies due to the locality of the convolutional layers. Transformers were introduced to address this challenge. In transformers with self -attention mechanism, even the first layer of information processing makes connections between distant image locations.Our paper presents a novel framework that bridges these two unique techniques, CNNs and transformers, to segment the gross tumor volume (GTV) accurately and efficiently in computed tomography (CT) images of non-small cell-lung cancer (NSCLC) patients. Methods: Under this framework, input of multiple resolution images was used with multi-depth backbones to retain the benefits of high-resolution and lowresolution images in the deep learning architecture. Furthermore, a deformable transformer was utilized to learn the long-range dependency on the extracted features. To reduce computational complexity and to efficiently process multiscale, multi-depth, high-resolution 3D images, this transformer pays attention to small key positions, which were identified by a self -attention mechanism. We evaluated the performance of the proposed framework on a NSCLC dataset which contains 563 training images and 113 test images. Our novel deep learning algorithm was benchmarked against five other similar deep learning models. Results: The experimental results indicate that our proposed framework outperforms other CNN-based,transformer-based,and hybrid methods in terms of Dice score (0.92) and Hausdorff Distance (1.33).Therefore,our proposed model could potentially improve the efficiency of auto-segmentation of early-stage NSCLC during the clinical workflow. This type of framework may potentially facilitate online adaptive radiotherapy, where an efficient auto-segmentation workflow is required. Conclusions: Our deep learning framework, based on CNN and transformer, performs auto-segmentation efficiently and could potentially assist clinical radiotherapy workflow. [ABSTRACT FROM AUTHOR]

Wind energy is one of the most significant renewable sources of energy while accurate and reliable wind power forecasting methods may greatly benefit power system planning and scheduling. Recently, many machine learning algorithms have shown significant advantages in how to extract temporal features for wind power forecasting. However, wind power curves in the time domain frequently display intermittent features and significant uncertainty, which is not favorable to precise and reliable forecasting. In this paper, the Diffusion and Channel Attention‐based Wind Power Forecasting (DC‐WPF) framework is proposed, which transforms wind power data into the frequency domain while applying advanced channel attention techniques to aid the model in capturing the frequency domain information and ultimately enhancing accuracy. With high‐accuracy results, DC‐WPF then proposes a diffusion‐based framework to transform the point forecasting results into probabilistic forecasts to capture the uncertainty. Finally, extensive experiments on six wind power plants show that our method can improve the point forecasting accuracy of wind power and provide advanced probabilistic forecasts at a multi‐time scale. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) modules are prone to short circuits, open circuits, cracks, which can bring serious harmful effects. It is difficult to establish the corresponding PV fault models to diagnose the status of PV strings. The paper proposes a machine learning‐based stacking classifier (MLSC) for accurate fault diagnosis of PV strings. Specifically, for the operating state of PV modules, the parameter sensitivity algorithm is used to analyze the impact of characteristic factors on the characteristics of PV modules. Then based on the characteristic factors (irradiance, temperature, current, and power), MLSC is proposed to realize the accurate fault diagnosis of PV strings. This structure of MLSC is to integrate all kinds of classifiers by stacking to play the characteristics of each classifier. It combines the characteristics of various types of machine learning algorithms to improve the overall classification effect by using the advantages of each classifier. Finally, experiments reveal that MLSC improves the accuracy of PV fault diagnosis. [ABSTRACT FROM AUTHOR]