Search

• An approach for pipelined event extraction consists of trigger identification, argument role recognition, and event construction. • BERT-based models are applied to three sub-tasks in biomedical event extraction. • N-ary relation extraction can effectively determine the validity of a candidate Binding event. • A pipelined biomedical event extraction rivaling joint learning. Biomedical event extraction is an information extraction task to obtain events from biomedical text, whose targets include the type, the trigger, and the respective arguments involved in an event. Traditional biomedical event extraction usually adopts a pipelined approach, which contains trigger identification, argument role recognition, and finally event construction either using specific rules or by machine learning. In this paper, we propose an n-ary relation extraction method based on the BERT pre-training model to construct Binding events, in order to capture the semantic information about an event's context and its participants. The experimental results show that our method achieves promising results on the GE11 and GE13 corpora of the BioNLP shared task with F1 scores of 63.14% and 59.40%, respectively. It demonstrates that by significantly improving the performance of Binding events, the overall performance of the pipelined event extraction approach or even exceeds those of current joint learning methods. [ABSTRACT FROM AUTHOR]

• Proposed a method (DEEP-EP) for prediction of Epigenetic Protein. • Features are extracted by DDE, DPC, and GAAC. • ERCNN is used for model training. • DEEP-EP secured the best performance. Epigenetic proteins (EP) play a role in the progression of a wide range of diseases, including autoimmune disorders, neurological disorders, and cancer. Recognizing their different functions has prompted researchers to investigate them as potential therapeutic targets and pharmacological targets. This paper proposes a novel deep learning-based model that accurately predicts EP. This study introduces a novel deep learning-based model that accurately predicts EP. Our approach entails generating two distinct datasets for training and evaluating the model. We then use three distinct strategies to transform protein sequences to numerical representations: Dipeptide Deviation from Expected Mean (DDE), Dipeptide Composition (DPC), and Group Amino Acid (GAAC). Following that, we train and compare the performance of four advanced deep learning models algorithms: Ensemble Residual Convolutional Neural Network (ERCNN), Generative Adversarial Network (GAN), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU). The DDE encoding combined with the ERCNN model demonstrates the best performance on both datasets. This study demonstrates deep learning's potential for precisely predicting EP, which can considerably accelerate research and streamline drug discovery efforts. This analytical method has the potential to find new therapeutic targets and advance our understanding of EP activities in disease. [ABSTRACT FROM AUTHOR]

To maintain animal welfare and reduce the economic loss associated with pastures, it is essential to monitor the health status of livestock. Accurate health assessments are the heart of the future of high-quality and high-yielding livestock production. As a non-invasive detection method, infrared thermography (IRT) technology can be used to indicate changes in thermal biological characteristics in animal metabolism, and it is a useful tool to detect issues in animal health. In addition, the development of emerging technologies represented by machine learning (ML) technology provides an opportunity to achieve non-contact, high-precision, automated cattle health assessments. Therefore, in this review, we examine the more than 100 related research papers to summarise and analyse the application of IRT and ML technology in cattle health management. Firstly, IRT and ML technology are introduced, including the concepts of acquiring of thermal images and obtaining parameter information. Secondly, the development status and research progress of IRT technology in cattle health assessment is summarised, focusing not only on bovine disease detection, including mastitis, lameness, respiratory diseases, etc., but also involving the indicators for assessing the health status, including physiological characteristics, stress, temperament and the oestrus of cattle. Thirdly, we focus on the tasks and application potential of ML and the deep learning (DL) algorithms in thermal infrared imaging data analysis before finally discussing the challenges associated with IRT and ML technology in the field of cattle health assessments are and examining the relevant suggestions put forward in this paper. • Infrared thermography is an effective tool in cattle health assessments. • The most widely used emissivity is 0.98, used in over 60% of researches. • Machine learning techniques in thermal imaging systems are investigated. • Machine learning in combination with thermal data has broad application. [ABSTRACT FROM AUTHOR]

• Application of ML methods in lasers is limited by a number of significant factors. • ML methods is often claimed where simple automation of control is introduced. • It is not clear, what kind of advantages will result from ML technologies in lasers. • Penetration of ML methods is frequently limited by the relatively low level of AI. • Presently, ML is not a universal method of photonics. Machine learning methods are being successfully applied in various domains of human activity, including optics. Can they become a universal instrument capable of improving user aspect of photonic devices? Is their application a necessary element of such improvement? Answers to fundamental questions arising from application of machine learning methods in ultrashort-pulsed lasers are discussed. Future prospects and current fundamental limitations of such methods are analysed. [ABSTRACT FROM AUTHOR]

Currently, deep learning has achieved remarkable success in estimating plant disease from unmanned aerial system (UAS) images. However, two critical challenges remain unexplored: spatiotemporal variations in disease symptoms and the domain shift between source and target datasets. To overcome these challenges, this paper proposes an approach that incorporates temporal aspects of disease progression using time series analysis. Spatiotemporal information is integrated by combining convolutional neural networks and bidirectional long-short term memory (CNN-BiLSTM) to classify the disease into five severity levels. Various feature extraction methods, including both handcrafted and CNN-based feature extractors, are evaluated. Furthermore, to tackle the problem of domain shift, a feature-level domain adaptation method is proposed. This method aims to learn transferable feature representations that remain consistent despite variations between source and target datasets. This approach enhances the spatiotemporal transferability of the CNN-BiLSTM model, enabling the effective utilisation of historical datasets. The study demonstrates that the CNN-BiLSTM model outperforms traditional time-independent machine-learning methods that rely on handcrafted features. Specifically, the Resnet101-BiLSTM model achieves the highest overall classification accuracy of 89.7% among all tested models evaluated on a one-year dataset. Moreover, it shows superior generalisation with 72.7% accuracy for cross-spatiotemporal disease severity classification using domain adaptation, as demonstrated through two-year experiments. By reducing the domain shift of source and target datasets and harnessing time series high-resolution images obtained throughout the crop growing season, this hybrid approach has substantial potential to advance the assessment of crop disease severity in field conditions. • Compared different CNN-based feature extractors for FOV4 symptom detection in UAS images. • Developed a BiLSTM model for temporal analysis in UAS datasets. • Use of domain adaptation enhanced model generalization. • CNN-BiLSTM with CORAL achieved 72.7% accuracy, proving its effectiveness in diverse real-world applications. [ABSTRACT FROM AUTHOR]

• We introduce a hexagonal convolution neural network for images with hexagonal pixels. • We applied hexCNN to segment spatially resolved transcriptomics data. • HexCNN achieved greater segmentation accuracies than state-of-the-art GNN models. • We noticed considerable dropout events and batch effects hindering further progress. Spatial transcriptomics is a rapidly evolving field that enables researchers to capture comprehensive molecular profiles while preserving information about the physical locations. One major challenge in this research area involves the identification of spatial domains, which are distinct regions characterized by unique gene expression patterns. However, current unsupervised methods have struggled to perform well in this regard due to the presence of high levels of noise and dropout events in spatial transcriptomic profiles. In this paper, we propose a novel hexagonal Convolutional Neural Network (hexCNN) for hexagonal image segmentation on spatially resolved transcriptomics. To address the problem of noise and dropout occurrences within spatial transcriptomics data, we first extend an unsupervised algorithm to a supervised learning method that can identify useful features and reduce noise hindrance. Then, inspired by the classical convolution in convolutional neural networks (CNNs), we designed a regular hexagonal convolution to compensate for the missing gene expression patterns from adjacent spots. We evaluated the performance of hexCNN by applying it to the DLPFC dataset. The results show that hexCNN achieves a classification accuracy of 86.8% and an average Rand index (ARI) of 77.1% (1.4% and 2.5% higher than those of GNNs). The results also demonstrate that hexCNN is capable of removing the noise caused by batch effect while preserving the biological signal differences. [ABSTRACT FROM AUTHOR]

The establishment of a bio-based circular economy is imperative in tackling the climate crisis and advancing sustainable development. In this realm, the creation of microbial cell factories is central to generating a variety of chemicals and materials. The design of metabolic pathways is crucial in shaping these microbial cell factories, especially when it comes to producing chemicals with yet-to-be-discovered biosynthetic routes. To aid in navigating the complexities of chemical and metabolic domains, computer-supported tools for metabolic pathway design have emerged. In this paper, we evaluate how digital strategies can be employed for pathway prediction and enzyme discovery. Additionally, we touch upon the recent strides made in using deep learning techniques for metabolic pathway prediction. These computational tools and strategies streamline the design of metabolic pathways, facilitating the development of microbial cell factories. Leveraging the capabilities of deep learning in metabolic pathway design is profoundly promising, potentially hastening the advent of a bio-based circular economy. [Display omitted] • Various computational methodologies have emerged for metabolic pathway design. • Deep learning facilitates enzyme discovery in pathway design. • Deep learning approaches in single- and multi-step pathway prediction are reviewed. • Deep learning techniques enhance the construction of microbial cell factories. • Computational guidelines are offered for experimental researchers. [ABSTRACT FROM AUTHOR]

The functional connectivity patterns of the brain during resting state are closely related to an individual's cognition, emotion, behavior, and social interactions, making it an important research method to measure personality traits in an unbiased way, replacing traditional paper-and-pencil tests. However, due to the dynamic nature of the brain, whether the changes in functional connectivity caused by age can stably map onto personality traits has not been previously investigated. This study focuses on whether network features that are significantly related to personality traits can effectively distinguish subjects with different personality traits, and whether these network features vary across different periods of adulthood. The study included 343 healthy adult participants, divided into early adulthood and middle adulthood groups according to the age threshold of 35. Resting-state functional magnetic resonance imaging (fMRI) and the Big Five personality questionnaire were collected. we investigated the relationship between personality traits and intrinsic whole-brain functional connectome. We then used support vector machine (SVM) to evaluate the performance of personality network features in distinguishing subjects with high and low scores in the early-adulthood sample, and cross-validated in the mid-adulthood sample. Additionally, edge-based analysis (NBS) was used to explore the stability of personality networks across the two age samples. Our results show that the network features corresponding to openness personality trait are stable and can effectively differentiate subjects with different scores in both age samples. Furthermore, this study found that these network features vary to some extent across different periods of adulthood. These findings provide new evidence and insights into the application of resting-state functional connectivity patterns in measuring personality traits and help us better understand the dynamic characteristics of the human brain. • Application of resting-state functional connectivity patterns in measuring personality traits. • The network features corresponding to openness personality trait are stable. • Network features vary to some extent across different periods of adulthood. [ABSTRACT FROM AUTHOR]

Assisted airflow can change the porosity within the canopy to achieve whole-plant coverage and uniform deposition of droplets. However, it is difficult to simulate the temporal and spatial distribution characteristics of the airflow field within the canopy because of the interaction between the assisted airflow and the leaves. This paper proposed and developed a method to predict the airflow field using fluid–structure interaction (FSI) simulation and machine-learning (ML) methods. Firstly, a 3D virtual plant model was established to describe the leaf structure in the canopy. Secondly, the flow field of leaves interacting with airflow was simulated by co-simulation with structural explicit Finite Element (FE) solver and lattice Boltzmann (LB) solver. Indoor artificial cotton plants were constructed to verify accuracy of the simulation. Finally, artificial neural network (ANN), random forest (RF), and support vector regression (SVR) models were trained based upon the results of a large amount of simulation training and test datasets. The training results showed that the RF and FSI simulation results match the coefficient of determination R2 of 0.9860 and root mean square error (RMSE) of 0.3017 well. The novel combination of computational fluid dynamics and ML improves simulation eēēfficiency, reduces time and computational cost, and provides a basis to select reasonable assisted airflow parameters before precision spraying. • Airflow velocity field in canopy predicted by using FSI and machine-learning. • Interaction between leaves and airflow is co-simulated by FE and LB methods. • Co-simulation results verified by measured data. • Machine-learning methods compared in approximation of co-simulation results. • This approach can be useful for optimising spray parameters. [ABSTRACT FROM AUTHOR]

• We develop a novel RNA secondary structure prediction algorithm based on the Conditional Deep Convolutional Generative Adversarial Network (CDCGAN) model. • MSFF-CDCGAN proposes a novel image-like representation of RNA structures to expand the original RNA data set. • MSFF-CDCGAN can predict long-sequence RNAs and pseudoknots. Access to RNA secondary structure is a prerequisite for understanding and mastering RNA function. RNA secondary structures play an important role in cells, they can cause or contribute to neurological disorders and can be applied in the medical field. However, the experimental method to obtain RNA secondary structure is costly, laborious and not universal. Although computational methods can predict RNA secondary structure more accurately for short-sequence RNAs, it cannot predict long-sequence RNAs and pseudoknot, which is the bottleneck of RNA secondary structure prediction at present. In recent years, researchers have attempted to use deep learning algorithms to predict RNA secondary structure and have achieved results. However, the small amount of data on the secondary structure of long-sequence RNAs leads to the low accuracy of deep learning methods to predict the secondary structure of RNAs across races. Similarly, RNA structure with pseudoknot is very complex and insufficient data caused the deep learning algorithm to struggle to predict the secondary structure of RNA containing pseudoknots. The RNA data are encoded into grayscale images by a unique encoding method based on the real RNA secondary structure and sequence information. Then, this paper reasonably expands the image data to increase the amount of RNA data, solves the problem of insufficient data for predicting long sequences and RNA secondary structure with pseudoknots in current deep learning methods, and provides a good data foundation for deep learning.The article proposes a multi-scale feature fusion Conditional Deep Convolutional Generative Adversarial Network prediction model (MSFF-CDCGAN) based on the improved Conditional Deep Convolutional Generative Adversarial Network (CDCGAN) model to predict RNA secondary structure. The experimental results showed that the MSFF-CDCGAN model could predict long-sequence RNAs and pseudoknots more accurately than traditional prediction methods. This paper introduces Generative Adversarial Network (GAN) to RNA secondary structure prediction for the first time. It uses a unique image encoding approach to expand the original RNA data set, thus transforming the structure prediction problem into an image analysis problem and effectively solving the bottleneck in RNA secondary structure prediction. [ABSTRACT FROM AUTHOR]

• Novel Photonic Device Development : The paper introduces a groundbreaking approach to create a photonic device for chemical applications, utilizing an evanescent wave absorption technique-based optical fiber probe. • Free-base Porphyrin Monolayering: The sensing probe incorporates a Tetraamine porphyrin (TAPP) monolayer, exploiting the unique optical properties of TAPP to enhance chemical sensing capabilities through the optical fiber. • Distinct Optical Patterns: The study focuses on monitoring interactions between TAPP and nitrate and chloride ions in the solution phase, emphasizing on absorption spectra variations of porphyrin molecules significantly in Soret and Q-bands. Distinct optical patterns emerge from the interaction, and the paper thoroughly analyses ion-dependent shifts in both the bands across eight samples of nitrates and chlorides. • Spectral Pattern Recognition: It employs unsupervised learning algorithms for spectral pattern recognition, allowing the discernment of ion groups based on their unique optical signatures. The use of PCA and Dtrend techniques helps to extract significant data to cluster different compounds. The sensor probe however exhibits remarkable sensitivity to nitrate and chloride ions, showcasing an impressive rapid response time of 2-3 s. • Practical Implications: The findings highlight the potential practical applications of the developed photonic device, emphasizing its utility in environmental monitoring and chemical analysis. The study positions porphyrin-based optical fiber sensor as a valuable technology, demonstrating their efficacy in detecting and analysing chemical compounds, particularly nitrate and chloride ions. The paper introduces a novel approach to develop a photonic device for chemical applications using an evanescent wave absorption technique-based optical fiber probe layered with a Tetraamine porphyrin (TAPP) monolayer exploiting the optical properties of TAPP. The interactions between the TAPP and nitrate and chloride ions in the solution phase were monitored and the changes in the absorption spectra of TAPP molecules were recorded. Distinct optical patterns emerge, and ion-dependent shifts in the Soret and Q-bands are analyzed for eight samples of nitrates and chlorides. Principal Component Analysis (PCA) is employed to discern ion groups based on the spectral pattern recognition. These fiber probes exhibit sensitivity to nitrate and chloride ions, with enhanced selectivity, robustness, and a rapid response time of 2–3 seconds. The study demonstrates the emergence of porphyrin-based optical fiber sensors as a useful sensor technology in environmental monitoring. [ABSTRACT FROM AUTHOR]

In the context of China's efforts to combat climate change and promote sustainable development, the solid waste treatment industry's environmental, social, and corporate governance (ESG) performance is receiving significant attention. To comprehensively assess the ESG performance of the solid waste treatment industry and identify company types, this study constructs a targeted ESG evaluation index system based on existing literature, SASB industry standards, and company reports and utilizes a random forest approach combined with K-means clustering to determine indicator weights. Based on this index system, the paper evaluates the ESG performance of 71 solid waste disposal companies (SWDCs) from 2013 to 2021 and identifies their ESG types from static and dynamic perspectives. In the static view, company types are determined based on annual ESG performance, while the dynamic view considers time-series changes to observe the evolution of company ESG types. The results show that the overall ESG performance of SWDCs falls within the 2-8-point range, indicating a noticeable high-low imbalance. Key initiatives to improve ESG performance in this industry include enhancing waste management measures, developing emergency plans, and reinforcing ESG disclosure. From a static perspective, this paper can identify companies into three categories: delayed development, single-wheel-driven, and coordinated development. Finally, from a dynamic perspective considering the time factor, companies are further subdivided into five types: continual leading, growth catch-up, slow progress, fluctuating change, and retrogressive inertia. This study not only provides targeted recommendations for different types of ESG companies but also helps various sectors of society better understand the ESG conditions of this high environmental risk industry, thereby enhancing the regulation and support for its sustainable development. [Display omitted] • ESG evaluation index system for solid waste disposal companies is proposed. • A random forest method based on k-means clustering is used to construct the index. • Comparing E, S, and G scores with industry averages to identify static ESG types. • Analyzing trends in annual static ESG types to identify dynamic ESG types. • Identify companies as three static ESG types and five dynamic ESG types. [ABSTRACT FROM AUTHOR]

In the context of carbon neutrality target, renewable energy sources have been transforming from "supplementary energy" to "main energy", which have promoted the green and low-carbon transition of global energy supply system. In-depth analyzing the spatial patterns and driving mechanisms of renewable energy expansion are of significance for optimizing the spatial layout of clean power, and avoiding the phenomenon of wind and solar power curtailment. In this paper, we proposed an ensemble learning model to examine the nonlinear effects of physical geography, resource endowment, and socio-economic factors on solar photovoltaic (PV) capacity at the prefecture-level city scale in China. Using the city-level multi-sources geospatial big data, we extensively collected a total of 175 related explanatory variables and cumulative installed capacity of solar PV power for 295 prefecture-level cities of China. The recursive feature elimination algorithm (SVM-REF) is firstly used to extract the optimal feature subset of urban PV capacity from multi-dimensional features variables. Furthermore, three advanced machine learning models (random forest, decision tree, extreme gradient boosting) are developed to identify the key influencing factors and nonlinear driving effect of urban solar PV power expansion in China. The results show that China's PV installation capacity is highly concentrated in Northern and Northwest parts of China, with the occupancy over 70% in 2019. Moreover, the XGBoost model has the best prediction accuracy (R2 = 0.97) among three methods. We also found that total amount of urban water resources, average solar radiation, and population density are the most important controlling factors for urban solar PV capacity expansion in China, with contribution of 35.6%, 17.7%, and 13.3%, respectively. We suggested that urban solar PV layout mode in China is recommended to gradually shift from resource orientation to the "resource-environment-demand" comprehensive orientation. The paper provides a replicable, scalable machine learning models for simulating solar PV power capacity at the prefecture-level city scale, and serves as a motivation for decision-making reference of the macro siting optimization and sustainable development of China's green power industry. • This study examines the impact of high-dimensional features variables on urban solar energy development. • Over 70% of solar PV installation capacity is concentrated in Northern and Northwest parts of China. • Water resources, solar radiation, population density have significant impact on solar PV distribution. • Solar PV distribution in China should shift from resource orientation to the comprehensive orientation. [ABSTRACT FROM AUTHOR]

This paper introduces a novel machine learning-based optimization strategy for multi-functional acoustic black hole (ABH) metaplates. The primary objective is to achieve a multi-functional metaplate with excellent performance in elastic wave attenuation and load-bearing capacity simultaneously. The paper begins by describing the design of nanocomposite ABH metaplates, presenting a new pathway to realize multi-functional metaplates. Then, a semi-analytical method, based on plate theory and the Bloch–Floquet theorem, is introduced to consider the band structure of the nanocomposite metaplates. Through systematic analysis, the impacts of the ABH effect, nanocomposite reinforcements, and the viscoelastic damping layer on the bandgaps and strain energy compliance are highlighted. Meanwhile, two optimization objectives representing bandgap characteristics and in-plane stiffness are derived respectively. Subsequently, a deep learning surrogate model is employed to establish a relationship involving significant parameters with the optimization objectives. The performance evaluation confirms accuracy and computational speed of the surrogate model. Finally, an optimization strategy based on deep reinforcement learning is proposed to obtain multi-functional metaplates with superior bandgaps, enhanced in-plane stiffness, or both. The robustness and efficiency of the strategy are demonstrated under different tests. The results show that the proposed strategy can achieve identical results as the genetic algorithm and nondominated sorting genetic algorithm-II, while surpassing them in computational efficiency and balancing multiple objectives. The findings of this study serve as valuable references for the future development and application of multi-functional advanced metamaterials. [ABSTRACT FROM AUTHOR]

Federated Learning coordinates many mobile devices to train an artificial intelligence model while preserving data privacy collaboratively. Mobile devices are usually equipped with totally different hardware configurations, leading to various training capabilities. At the same time, the distribution of the local training data is highly heterogeneous across different clients. Randomly selecting the clients to participate in the training process results in poor model performance and low system efficiency. In this paper, we propose GraphCS, a graph-based client selection framework for heterogeneity in Federated Learning. GraphCS first measures the distribution coupling across the clients via the model gradients. After that, it divides the clients into different groups according to the diversity of the local datasets. At the same time, it well estimates the runtime training capability of each client by jointly considering the hardware configuration and resource contention caused by the concurrently running apps. With the distribution coupling information and runtime training capability, GraphCS selects the best clients in order to well balance the model accuracy and overall training progress. We evaluate the performance of GraphCS with mobile devices with different hardware configurations on various datasets. The experiment results show that our approach improves model accuracy up to 45.69%. Meanwhile, it reduces communication and computation overhead 87.35% and 89.48% at best, respectively. Furthermore, GraphCS accelerates the overall training process up to 35×. • We observe that the distribution of the training data can be reflected by the gradient of a machine learning model. • We observe that the training capability is jointly affected by the hardware configuration and resource contention. • we design a framework selects the best clients with diverse local datasets and highest runtime training capability. • We prototype GraphCS on a Federated system consisting of mobile devices with heterogeneous hardware configurations. [ABSTRACT FROM AUTHOR]

Extreme-scale computing involves hundreds of millions of threads with multi-level parallelism running on large-scale hierarchical and heterogeneous hardware. Some OpenMP multi-threaded applications increasingly suffer from runtime hidden behaviors owning to shared resource contention as well as software- and hardware-related problems. Such hidden behaviors can result in failure and inefficiencies and are among the main challenges in system resiliency. To minimize the impact of hidden behaviors, one must quickly and accurately detect and diagnose the hidden behaviors that cause the failures. However, it is difficult to identify hidden behaviors in the dynamic and noisy data collected by OpenMP multi-threaded monitoring infrastructures. This paper presents an anthropomorphic diagnosis framework for hidden behaviors of OpenMP multi-threaded applications. In the framework, we first design injected heartbeat functions for OpenMP multi-threaded applications. Then, we leverage the heartbeat sequences to extract features of hidden behaviors. Finally, we develop a feature learning-based algorithm using heartbeat analysis, namely HSA, to diagnose hidden behaviors. To evaluate our framework, the NAS Parallel NPB benchmark, EPCC OpenMP micro-benchmark suite, and Jacobi benchmark are used to test the performance of our proposed framework. The experimental results demonstrate that our framework successfully identifies 90.3% of the injected hidden behaviors of OpenMP multi-threaded applications while acquiring low overhead. • The anthropomorphic framework is proposed for diagnosing hidden behaviors. • The framework based on heartbeats supports multi-threaded OpenMP applications. • Small-size samples also demonstrate the high efficiency of this framework. • The framework is lower overhead and is more accurate than the state-of-the-art. • The framework supports extension and specificity in most of our experiments. [ABSTRACT FROM AUTHOR]

Cow lameness is a complex locomotion behaviour, and effective characteristics are the key to identifying early lameness. Machine learning methods were used to quantify the movement of the hooves and head of cows, and they showed the possibility of using the head- and back-hoof linkage features extracted from motion analysis to classify early lameness. Firstly, the key points of the body in the side-view walking videos were tracked by DeepLabCut (DLC). Based on the curves of hoof movement and head swing, the head-hoof linkage pattern was analysed. Second, the curve of cow's back was extracted and the back-hoof linkage feature was built when the hoof touched the ground. At the same time, the movement curves were analysed to extract five other gait characteristics, including asymmetry of stride length, tracking up, asymmetry in the proportion of supporting phase, landing speed, and moving speed. Multiple models were trained on a dataset containing 212 videos, and 10-fold cross-validation was used to verify the performance of the algorithm. The classification performance was improved by optimising the model and algorithm. Overall accuracy and recall were 89.2% and 90.7%, respectively. The scores of the importance of features calculated by the Chi-square test showed that the head- and back-hoof linkage features play an important role in the classification of early lame cows. The hooves and their linkage features with the head and back of cows proposed in this paper can thus effectively detect early lameness in cows. • DeepLabCut was used to track four hooves and head of walking cow. • Head- and back-hoof linkage features was analysed. • Seven lameness indicators were used to build the model. • The recall of classification for early lame cows was 90.7%. [ABSTRACT FROM AUTHOR]

One of the key objectives in many fields in machine learning is to discover causal relationships among a set of variables from observational data. In linear non-Gaussian acyclic models (LiNGAM), it can be shown that the true underlying causal structure can be identified uniquely from merely observational data. The DirectLiNGAM algorithm is a well-known solution to learn the true causal structure in a high dimensional setting. DirectLiNGAM algorithm executes in a sequence of iterations and it performs a set of comparisons between pairs of variables in each iteration. Unfortunately, the runtime of this algorithm grows significantly as the number of variables increases. In this paper, we propose a parallel algorithm, called ParaLiNGAM, to learn casual structures based on DirectLiNGAM algorithm. We propose a threshold mechanism that can reduce the number of comparisons remarkably compared with the sequential solution. Moreover, in order to further reduce runtime, we employ a messaging mechanism between workers. We also present an implementation of ParaLiNGAM on GPU, considering hardware constraints. Experimental results on synthetic and real data show that our proposed solution outperforms DirectLiNGAM by a factor up to 4788X, and by a median of 2344X. • A scalable algorithm for learning causal structures in linear non-Gaussian models. • Significant speedup by selecting the necessary computations judiciously. • Speedup ratio of up to 4788 on GPUs in real-world and synthetic datasets. [ABSTRACT FROM AUTHOR]

Although code generation for Convolution Neural Network (CNN) models has been extensively studied, performing efficient data slicing and parallelization for highly-constrained Multicore Neural Processor Units (NPUs) is still a challenging problem. Given the size of convolutions' input/output tensors and the small footprint of NPU on-chip memories, minimizing memory transactions while maximizing parallelism and MAC utilization are central to any effective solution. This paper proposes a TensorFlow XLA/LLVM compiler optimization pass for Multicore NPUs, called Tensor Slicing Optimization (TSO), which: (a) maximizes convolution parallelism and memory usage across NPU cores; and (b) reduces data transfers between host and NPU on-chip memories by using DRAM memory burst time estimates to guide tensor slicing. To evaluate the proposed approach, a set of experiments was performed using the NeuroMorphic Processor (NMP), a multicore NPU containing 32 RISC-V cores extended with novel CNN instructions. Experimental results show that TSO is capable of identifying the best tensor slicing that minimizes execution time for a set of CNN models. Speed-ups of up to 21.7% result when comparing the TSO burst-based technique to a no-burst data slicing approach. To validate the generality of the TSO approach, the algorithm was also ported to the Glow Machine Learning framework. The performance of the models were measured on both Glow and TensorFlow XLA/LLVM compilers, revealing similar results. • A burst-based cost model for Tensor Slicing Optimization. • Reducing data transfer between host and NPU on-chip memories. • Maximizing Convolution parallelism and memory reuse. [ABSTRACT FROM AUTHOR]

There are massive jobs submitted in the supercomputer, and the job management system is typically deployed to schedule these jobs and allocate compute resources. FCFS (First Come First Serve) is a popular scheduling policy and the job's priority is determined based on the arrival time. However, under the FCFS strategy, if existing idle resources cannot meet the requirement of the head job in the waiting queue, they cannot be allocated to other jobs, which suffers from resource waste. To optimize the resource utilization, the backfilling method is proposed, which allocates the reserved idle compute nodes to a small-size and short-running non-head job, on the premise of not delaying the original head job. Obtaining the job's runtime in advance is necessary for backfilling and the traditional method relies on the user's estimation. Unfortunately, the estimated runtime provided by users is generally overestimated. Many studies extract features from historical job logs and adopt machine learning to predict the runtime. However, traditional features are insufficient to characterize the job. In this paper, we collect job logs from two supercomputers and present a novel runtime prediction framework called PREP. PREP explores the job's running path as a new feature, which implies plentiful information about the job's properties, such as the user, the project, the scale of data sets, and the parameters used. As there is a strong correlation between the job's runtime and its running path, we group jobs with similar paths into a cluster and train a runtime prediction model for each cluster respectively. Extensive evaluations demonstrate that introducing the new feature can achieve higher prediction accuracy (88.5% and 82.3% in two production supercomputers respectively), and our framework has a more desirable prediction performance than other popular strategies like Last-2 and IRPA. In addition, the predicted runtime is inserted into the real job trace of a slurm simulator to verify the advantages of PREP. • PREP explores the job's running path as a new feature to support runtime prediction. • A strong correlation between the job's runtime and its running path is evaluated. • Multiple machine learning algorithms are adopted and compared when predicting. • PREP framework suits different types of supercomputers and gain desirable prediction result. [ABSTRACT FROM AUTHOR]

Automatic code generation is frequently used to create implementations of algorithms specifically tuned to particular hardware and application parameters. The code generation process involves the selection of adequate code transformations, tuning parameters, and parallelization strategies. We propose an alternative to time-intensive autotuning, scenario-specific performance models, or black-box machine learning to select the best-performing configuration. This paper identifies the relevant performance-defining mechanisms for memory-intensive GPU applications through a performance model coupled with an analytic hardware metric estimator. This enables a quick exploration of large configuration spaces to identify highly efficient code candidates with high accuracy. We examine the changes of the A100 GPU architecture compared to the predecessor V100 and address the challenges of how to model the data transfer volumes through the new memory hierarchy. We show how our method can be coupled to the "pystencils" stencil code generator, which is used to generate kernels for a range-four 3D-25pt stencil and a complex two-phase fluid solver based on the Lattice Boltzmann Method. For both, it delivers a ranking that can be used to select the best-performing candidate. The method is not limited to stencil kernels but can be integrated into any code generator that can generate the required address expressions. • Analytical Performance Modeling helps to find the best tuning parameters for code generation. • Analytical Performance Modeling gives insight that is unavailable to black box machine learning or auto tuning. • The thread block size is a decisive factor for GPU cache data volumes and performance. • GPU cache behavior and GPU performance can be accurately predicted based only on high level information. [ABSTRACT FROM AUTHOR]

Semi-active suspensions are important components for improving vehicle ride comfort. In this paper, a new road unevenness classification method that is based on tread band vibrations is proposed. Moreover, this method is implemented in the control algorithm of a semi-active suspension with a magnetorheological damper (MRD). The core contributions of this paper include establishing the simulation environment for the tread band vibration based on the rigid-flexible coupling ring tire model and the hardware testing platform based on an intelligent tire and a 1/4 vehicle vibration bench. In this testing platform, an intelligent tire sensor is installed in the tire to reflect the tread band vibration. The comparison of different machine learning algorithms and measured accelerations indicates the effectiveness of using the decision tree algorithm and the tread band vibration for road classification. Furthermore, a hardware architecture is proposed in this paper for real-time communication between wirelessly transmitted intelligent tire acceleration signals and a suspension controller, achieving online classification and adaptive adjustment of the optimal control parameters for the semi-active suspension. In summary, intelligent tires and suspension control systems are successfully integrated in this study, providing the possibility and basis for developing more complex general chassis control systems that include intelligent tires. [ABSTRACT FROM AUTHOR]

The popularity of Machine Learning (ML) has extended to numerous disciplines, including the domain of Network-on-chips (NoCs), leading to a consequential impact. Recent works have explored ML models' applicability for NoCs design, optimization, and performance evaluation. ML-based NoCs design has demonstrated superior performance to heuristic methods employed by human experts in NoCs design. This has facilitated a tight collaboration between ML and NoCs research, offering novel perspectives and optimization strategies to advance NoCs design. In this paper, we present a comprehensive survey into implementing ML techniques for NoCs. Initially, we provide an overview of ML-based research for NoCs in two aspects: (i) the adoption of ML for performance modeling and prediction and (ii) ML-based for NoCs design, including individual components (such as routing algorithm, arbitration, traffic control, etc.). Subsequently, we summarize the challenges and difficulties in designing NoCs for applying ML techniques and discuss the preliminary solutions to these issues. Finally, we prospect the perspective on future research directions for expanding the application of ML techniques to diverse scenarios of NoCs, exploring the adoption of ML techniques for NoCs design automation. We expect this paper can be helpful for design experts to optimize NoCs using ML techniques, leading to high-performance, energy-efficient, and easy-to-implement NoCs. • Introduction of applying common Machine Learning (ML) techniques for Network-on-Chips (NoCs). • A comprehensive survey of ML for NoCs from performance prediction and NoCs design perspective. • ML-based for NoCs performance modeling, prediction, and design. • Discussion of the challenges in ML-based NoCs and the perspective on future research directions. [ABSTRACT FROM AUTHOR]

The recent advances in machine translation (MT) offer an appealing and low-cost solution to overcome language barriers in multiple contexts (e.g., travelling, cultural interaction, digital content localisation). However, highly-technical domains typically exhibiting as long, complex, and specialised texts as the healthcare sector, pose multiple challenges to the effective and risk-safe use of MT. To examine how MT nowadays assists written/verbal health communication and because of the existing considerable heterogeneity in technological enablers, language pairs and user groups, training approaches, evaluation processes, and users" requirements, we propose in this paper a methodological multi-criteria literature review based on current guidelines in computer science research and grounded on a customised configuration of the PRISMA methodology, normally used to perform meta-analyses on clinical trials. The review focuses on language-to-language medical MT, covers the time period January 2015–February 2023, and only refers to articles written in English that are accessible via four scientific online digital libraries. Articles are ranked according to a meta-evaluation scoring method for MT scientific credibility along with a scoring for assessing the scope of MT in healthcare. Finally, a guideline to properly design a study about MT in healthcare is also proposed. The review included a final set of 58 articles from journals (n = 30) and conference proceedings (n = 28), considering 48 different language combinations. We identified a predominance of English-to-Spanish (n = 19) and English-to-Chinese (n = 16) implementations, mainly tailored to medical staff only (n = 14) or along with patients (n = 12). Included papers addressed clinical communication (n = 21) and health education (n = 37). Unidirectional real-time bilingual MT (n = 24) was the most frequent configuration. MT implementations were dominated by Google Translate (n = 22) often used as baseline, OpenNMT (n = 12), or Moses (n = 11). Training and evaluation approaches varied considerably, while deployment and pre-/post-editing were rarely described with an adequate level of detail. Even if a significant number of articles reported that the proposed MT solutions were effective when translating (bio)medical texts, only a subset of them complied with rigorous translation quality assessment criteria (e.g., use of automatic metrics better related to human ranking than BLEU or statistical significance testing). Nevertheless, MT can be a valid support/supplement in health communication but to cope with issues in fluency, accuracy, unnatural translations, domain-adequacy, and potential safety risks (for highly-sensitive documents), appropriate MT training is essential, along with in-domain human post-editing. The presence of in-domain training text corpora has also proven to be beneficial. Finally, guidelines about how to design studies on MT in healthcare are also proposed to engage more researchers in this field. • Machine Translation (MT) is a tempting low-cost solution to lower language barriers. • When used in the health sector, MT is effective for translating non-sensitive texts. • Even neural MT solutions still pose safety concerns in specialised medical contexts. • MT in healthcare is a valuable support but requires appropriate quality assessment. • Shared guidelines to design and evaluate studies on MT in healthcare are essential. [Display omitted] [ABSTRACT FROM AUTHOR]

This paper presents a new framework for stochastic updating of a finite element model for a composite plate, considering the influence of temperature on Lamb wave propagation. The framework involves deterministic updating to optimize mechanical properties and stochastic updating to derive probability density functions for key parameters. It utilizes sensitivity analysis and Bayesian inference with Markov-Chain Monte Carlo simulations and the Metropolis–Hastings sampling algorithm. This paper proposes a machine learning surrogate model based on artificial neural networks to improve computational efficiency. This surrogate modeling approach allows parallelized Monte Carlo simulations, reducing updating time significantly without compromising the accuracy of the resulting probability density functions for model parameters. These advancements show a promising way to enhance composite plate modeling and Lamb wave propagation studies, providing a more efficient and accurate approach to verify and validate finite element models with potential applications in engineering simulations. [ABSTRACT FROM AUTHOR]

Domain adaptation has achieved great success in using labeled source domain samples to identify unlabeled target domain samples. Here, we aim to solve the open-set domain adaptation, which is different from the closed-set domain adaptation in that it contains categories in target domain that do not appear in source domain. To solve this problem, this paper proposes open-set domain adaptation model based on subdomain alignment, which uses variable weights for discriminative training of unknown samples in target domain. Aiming at the distribution differences between domains, the model aligns the distributions of the category subspaces of source and target domains, enhancing the distribution similarity within the subspaces of the same category. Through experiments on different domain adaptation datasets, the results show that the model proposed in this paper effectively improves the accuracy of open-set domain adaptation classification. [ABSTRACT FROM AUTHOR]

Smart mobile devices have recently emerged as a promising computing platform for computation tasks. However, the task performance is restricted by the computing power and battery capacity of mobile devices. Mobile edge computing, an extension of cloud computing, solves this problem well by providing computational support to mobile devices. In this paper, we discuss a mobile edge computing system with a server and multiple mobile devices that need to perform computation tasks with priorities. The limited resources of the mobile edge computing server and mobile device make it challenging to develop an offloading strategy to minimize both delay and energy consumption in the long term. To this end, an online algorithm is proposed, namely, the double reinforcement learning computation offloading (DRLCO) algorithm, which jointly decides the offloading decision, the CPU frequency, and transmit power for computation offloading. Concretely, we first formulate the power scheduling problem for mobile users to minimize energy consumption. Inspired by reinforcement learning, we solve the problem by presenting a power scheduling algorithm based on the deep deterministic policy gradient (DDPG). Then, we model the task offloading problem to minimize the delay of tasks and propose a double Deep Q-networks (DQN) based algorithm. In the decision-making process, we fully consider the influence of task queue information, channel state information, and task information. Moreover, we propose an adaptive prioritized experience replay algorithm to improve the model training efficiency. We conduct extensive simulations to verify the effectiveness of the scheme, and the simulation results show that compared with the conventional schemes, our method reduces the delay by 48% and the energy consumption by 53%. • An online computing offload model for mobile edge computing system. • Based on double DQN and DDPG to reduce delay and energy consumption. • An adaptive prioritized experience replay algorithm to improve training efficiency. [ABSTRACT FROM AUTHOR]

Predicting the performance of applications executed on GPUs is a great challenge and is essential for efficient job schedulers. There are different approaches to do this, namely analytical modeling and machine learning (ML) techniques. Machine learning requires large training sets and reliable features, nevertheless it can capture the interactions between architecture and software without manual intervention. In this paper, we compared a BSP-based analytical model to predict the time of execution of kernels executed over GPUs. The comparison was made using three different ML techniques. The analytical model is based on the number of computations and memory accesses of the GPU, with additional information on cache usage obtained from profiling. The ML techniques Linear Regression, Support Vector Machine, and Random Forest were evaluated over two scenarios: first, data input or features for ML techniques were the same as the analytical model and, second, using a process of feature extraction, which used correlation analysis and hierarchical clustering. Our experiments were conducted with 20 CUDA kernels, 11 of which belonged to 6 real-world applications of the Rodinia benchmark suite, and the other were classical matrix-vector applications commonly used for benchmarking. We collected data over 9 NVIDIA GPUs in different machines. We show that the analytical model performs better at predicting when applications scale regularly. For the analytical model a single parameter λ is capable of adjusting the predictions, minimizing the complex analysis in the applications. We show also that ML techniques obtained high accuracy when a process of feature extraction is implemented. Sets of 5 and 10 features were tested in two different ways, for unknown GPUs and for unknown Kernels. For ML experiments with a process of feature extractions, we got errors around 1.54% and 2.71%, for unknown GPUs and for unknown Kernels, respectively. [ABSTRACT FROM AUTHOR]

Codling moth (CM) (Cydia pomonella L.) is the most destructive pest for apples, causing large economic losses when not properly mitigated. Efficient detection methods can limit the spread of this pest in the apple supply chain. Non-destructive methods have several advantages over the current methods in that they can be applied to every apple (or a much larger sample) thereby reducing the possibility of missed detection. This paper examines the feasibility of acoustic impulse response methods for detecting CM larvae-infested apples. Experiments were performed on control and artificially infested apples from three different cultivars. Signals were recorded with a contact sensor, and 21 signal features were proposed and extracted to characterise relevant properties of the response. The 21 features were evaluated with 11 machine leaning algorithms to determine if the features or their subsets contained information that could reliability determine if an apple was/is infested. Classification test results using a 10-fold cross-validation indicated accuracy rates between 80% and 92% for Fuji apples, between 92% and 99% for Gala apples, and 63% and 97% for Granny Smith apples. The impulse response required between 60 and 80 ms for each apple (not counting setup/transition time). These results from this study suggest that active impulse response classification can potentially improve the detection of post-harvest apple CM infestation detection along the supply chain. • Acoustic impulse response signals were investigated for detection of codling moth in apples. • Ultrasonic sound from solenoid tapping were attenuated differently based on apple quality. • Ensemble methods were the better classifiers for differentiating signals from apples. • Classification rates for Gala were the best ranging between 0.92 and 0.99. [ABSTRACT FROM AUTHOR]

We study in this paper several problems at the intersection of decentralized optimization and online learning. Decentralized optimization plays a vital role in machine learning and has recently garnered much attention due to its inherent advantage in handling edge computations. Many decentralized optimization algorithms, both projection and projection-free algorithms with theoretical guarantees, have been proposed in the literature, focusing mainly on offline settings. However, for most real-world machine learning problems, the data is often revealed online, for example, in the case of recommender systems, image/video processing, and stock portfolio management. Therefore, in this work, we study decentralized optimization within the framework of online settings with constraints imposed on the optimization solutions (e.g., sparsity or low rank of matrices). More specifically, we consider the problem of optimizing an aggregate of convex loss functions that arrive over time such that their components are distributed over a connected network. We present a consensus-based online decentralized Frank-Wolfe algorithm that uses stochastic gradient estimates, which achieves an asymptotically tight regret guarantee of O (T) where T is a given time horizon. Furthermore, we demonstrate the performance of this algorithm for optimizing the online multiclass logistic regression model on real-world standard image datasets (M N I S T , C I F A R 10) by comparing with centralized online algorithms. We achieve better regret bounds than the previously best-known decentralized constrained online algorithms. [ABSTRACT FROM AUTHOR]

Recently, the Randomized Kaczmarz algorithm (RK) draws much attention because of its low computational complexity and less requirement on computer memory. Many existing results on analysis focus on the behavior of RK in Euclidean spaces, and typically derive exponential converge rates with the base tending to one, as the condition number of the system increases. The dependence on the condition number largely restricts the application of these estimates. There are also results using relaxation (i.e., small step-sizes tending to zero as the sample size increases) to achieve polynomial convergence rates of RK in Hilbert spaces. In this paper, we prove the weak convergence (with polynomial rates) of RK with constant step-size in Hilbert spaces. As a consequence, the strong convergence of RK in Euclidean spaces is obtained with condition number-free polynomial rates. In the setting with noisy data, we study the relaxation technique and obtain a strong convergence of RK in Hilbert spaces, with the rates arbitrarily close to the minimax optimal ones. We apply the analysis to reproducing kernel-based online gradient descent learning algorithms and improve the state-of-the-art convergence estimate in the literature. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has garnered increasing attention as a means to quantitatively analyze the growing and complex medical data to improve individualized patient care. We herein aim to critically examine the current state of ML in predicting surgical outcomes, evaluate the quality of currently available research, and propose areas of improvement for future uses of ML in surgery. A systematic review was conducted in accordance with the Preferred Reporting Items for a Systematic Review and Meta-Analysis (PRISMA) checklist. PubMed, MEDLINE, and Embase databases were reviewed under search syntax "machine learning" and "surgery" for papers published between 2015 and 2020. Of the initial 2677 studies, 45 papers met inclusion and exclusion criteria. Fourteen different subspecialties were represented with neurosurgery being most common. The most frequently used ML algorithms were random forest (n = 19), artificial neural network (n = 17), and logistic regression (n = 17). Common outcomes included postoperative mortality, complications, patient reported quality of life and pain improvement. All studies which compared ML algorithms to conventional studies which used area under the curve (AUC) to measure accuracy found improved outcome prediction with ML models. While still in its early stages, ML models offer surgeons an opportunity to capitalize on the myriad of clinical data available and improve individualized patient care. Limitations included heterogeneous outcome and imperfect quality of some of the papers. We therefore urge future research to agree upon methods of outcome reporting and require basic quality standards. [ABSTRACT FROM AUTHOR]

For data-parallel frameworks, their communication is highly structured. Coflow is a networking abstraction proposed for their all-or-nothing job-specific semantics. Minimizing coflow completion time (CCT) decreases the completion time of corresponding jobs. However, state-of-the-art coflow scheduling approaches suffer from several drawbacks. On the one hand, both sender-driven and receiver-driven scheduling approaches fail to achieve optimal especially when the bandwidth bottleneck exists. On the other hand, they fail to optimize the number of concurrent connections since the CCT can be prolonged due to too many or too few concurrent connections. In this paper, we propose Django, a bilateral coflow scheduling framework. We first use Support Vector Machine (SVM) as the machine learning model to automatically identify the optimal number of concurrent connections, i.e. , the queue limitation in the switch. Based on the predicted results, we further develop a set of distributed coflow scheduling algorithms in a scalable manner. Testbed experiments and trace-driven simulations show that Django can estimate the number of concurrent connections with an accuracy of 98%, reduce the average CCT and 95th percentile CCT by 15% and 40%, respectively. • State-of-the-art coflow scheduling approaches suffer from several drawbacks. • On the one hand, both sender-driven and receiver-driven scheduling approaches fail to achieve optimal especially when the bandwidth bottleneck exists. • On the other hand, they fail to optimize the number of concurrent connections since the CCT can be prolonged due to too many or too few concurrent connections. • In this paper, we propose Django, a bilateral coflow scheduling framework, which can automatically identify the optimal number of concurrent connections. • Testbed experiments and trace-driven simulations show that Django can estimate the number of concurrent connections with an accuracy of 98%, reduce the average CCT and tail CCT. [ABSTRACT FROM AUTHOR]

Many HPC applications suffer from a bottleneck in the shared caches, instruction execution units, I/O or memory bandwidth, even though the remaining resources may be underutilized. It is hard for developers and runtime systems to ensure that all critical resources are fully exploited by a single application, so an attractive technique for increasing HPC system utilization is to colocate multiple applications on the same server. When applications share critical resources, however, contention on shared resources may lead to reduced application performance. In this paper, we show that server efficiency can be improved by first modeling the expected performance degradation of colocated applications based on measured hardware performance counters, and then exploiting the model to determine an optimized mix of colocated applications. This paper presents a new intelligent resource manager and makes the following contributions: (1) a new machine learning model to predict the performance degradation of colocated applications based on hardware counters and (2) an intelligent scheduling scheme deployed on an existing resource manager to enable application co-scheduling with minimum performance degradation. Our results show that our approach achieves performance improvements of 7 % (avg) and 12 % (max) compared to the standard policy commonly used by existing job managers. • HPC systems can be improved by colocating jobs on same machine. • Jobs contending for shared resources may experience performance degradation. • Hardware counters and machine learning can characterize contention on shared resource. • Greedy strategy based on machine learning can improve job execution on batch systems. [ABSTRACT FROM AUTHOR]

Over the last two decades, research in hyperspectral imaging has been increasing and its use in horticulture is expected to be spreading in the coming years. The emerging techniques are currently gaining interest of the research community. However, there are still challenges to the applicability. In this review we demonstrate that hyperspectral imaging can be used as an effective tool for fruit, vegetables and mushrooms in assessing quality parameters related to well defined variables that can be analysed in the laboratory, as well as complex properties such as maturity, ripeness, detection of biotic defects, physiological disorders, mechanical damages, and sensory quality. Therefore, this paper starts by giving an overview of the quality concept of produce, measuring principles, theory and analysis of hyperspectral imaging systems. Then, emerging techniques to monitor and assess quality parameters, both pre- and postharvest, are described, as well as applications of these are reviewed and discussed. Afterwards, this review proceeds by illustrating the current and potential use of artificial intelligence and its subdomains, machine learning and deep learning, for hyperspectral imaging analysis in horticulture. Lastly, some challenges and considerations for future research are highlighted, including improvement of data availability, possible solutions for an improved integration of artificial intelligence and the transfer of knowledge from research parameters to parameters relevant for industrial stakeholders. • Hyperspectral imaging is an effective tool for in assessing quality parameters. • The most abundantly used wavelengths are 601–850 nm, used in over 50% of studies. • PLSR and SVM are most commonly used models for machine learning. • Deep learning in combination with hyperspectral data is unexplored in horticulture. • Improving availability, AI knowledge transfer and standardisation is recommended. [ABSTRACT FROM AUTHOR]

• An Accurate Contactless Sleep Apnea Detection Framework with Signal Processing and Machine Learning Methods was proposed. • The MDACM demodulation method combined with DC removal improved the accuracy of the radar sensor to monitor the respiratory signals. • Adequate features of respiratory signals combined with machine learning methods can be used as an effective tool for sleep apnea detection. • The oversampling approach ADASYN was used in our work, which well solved the problem of data imbalance and effectively improved the accuracy of classification. The detection of sleep apnea is critical for assessing sleep quality. It is also a proven biometric in diagnosing cardiovascular and other diseases. Recent studies have shown that radar-based non-contact vital sign monitoring system can effectively detect sleep apnea. However, the detection accuracy in the current study still needs to be improved. In this paper, we propose a sleep apnea detection framework based on FMCW radar. First, the radar system is employed to record the sleep data throughout the night with polysomnography (PSG) comparison. Then, in order to extract more accurate respiratory signal from the raw radar data, the signal processing methods are investigated to solve the observed discontinuity phenomenon. Finally, machine learning methods are adopted. The apneic and not-apneic events are classified accurately by selecting effective features of respiratory signal. As shown in the experimental results, the proposed system could achieve a good classification performance with an accuracy of 95.53%, a sensitivity of 72.60%, a specificity of 97.32%, a Kappa of 0.68, and an F-score of 0.84. [ABSTRACT FROM AUTHOR]

• A graph normalization method was proposed to integrate phylogenetic information for metagenomic host phenotype prediction. • The method learned better the structure of phylogenetic trees. • The proposed method enhanced the accuracy of machine learning and deep learning models in different metagenomic datasets. Microorganisms play important roles in our lives especially on metabolism and diseases. Determining the probability of human suffering from specific diseases and the severity of the disease based on microbial genes is the crucial research for understanding the relationship between microbes and diseases. Previous could extract the topological information of phylogenetic trees and integrate them to metagenomic datasets, thus enable classifiers to learn more information in limited datasets and thus improve the performance of the models. In this paper, we proposed a GNPI model to better learn the structure of phylogenetic trees. GNPI maintained the original vector format of metagenomic datasets, while previous research had to change the input form to matrices. The vector-like form of the input data can be easily adopted in the baseline machine learning models and is available for deep learning models. The datasets processed with GNPI help enhance the accuracy of machine learning and deep learning models in three different datasets. GNPI is an interpretable data processing method for host phenotype prediction and other bioinformatics tasks. [ABSTRACT FROM AUTHOR]

Accurate prediction of pig growth is an important tool for supporting sustainable global pork production, due to the potential benefits to farm management in monitoring growth according to target, promoting efficient use of resources and planning sale of finished animals. In this paper, a long short-term memory (LSTM) recurrent neural network architecture was designed to predict how long it would take for grower-finisher pigs housed in a climate-controlled building reflecting commercial practice to reach a target liveweight of 90 kg. To make these predictions, data on pig liveweight and food consumption were integrated, along with various combinations of environmental temperature recorded by the building control system and, to represent seasonality, encodings of day of the year. Also, ensembles were created and evaluated by averaging the predictions of multiple models, each trained with different combinations of input features, and comparisons were made between the performance of the LSTM models and other machine learning algorithms. Overall, the LSTM model achieved the best prediction performance, with a RMSE of 2.470 days and a Pearson's correlation coefficient of 0.962. Integrating both environmental temperature and seasonality data into the models generally resulted in an improvement in predictive performance. The results demonstrate the potential of LSTM models as a precision livestock farming tool for the early prediction of growth in commercial finisher pigs. • A machine learning pipeline for the forecasting of pig growth was designed. • Predicting the time to reach a target weight can improve data availability. • Specialised neural network architectures are very effective at predicting growth. • Utilising environmental temperatures can improve growth prediction accuracy. • Specialised algorithms can be used to remove outliers from non-cyclical time series. [ABSTRACT FROM AUTHOR]

Quantisation is a commonly applied technique to improve the efficiency of a neural network on edge devices. Many applications also require that a machine learning model extend its learning cycle into the field. Training a quantised neural network on edge devices is a non-trivial task since the resource available on the edge is limited. Most of the quantisation-aware training methods maintain a quantised model, as well as an extra full-precision model, which is used to prevent large accuracy losses. The keep of the full precision model is based on the assumption that there are sufficient memory and energy supply to the machine for training. The assumption is contradictory to the situation of edge AI. In this paper, we propose the Adaptive Precision Training method (APT), which only keeps a quantised model. The challenge is that a quantised model has difficulty in learning, due to the quantisation underflow issue. APT employs a metric called G a v g to quantify the learning ability of each layer and dynamically adjusts per-layer bitwidth to ensure the model can learn effectively. Experiments on image classification and text classification tasks suggest that APT trains quantised models effectively with limited accuracy loss. Compared with the 8-bit traditional QAT method, APT saves 60-72.5% memory space for model parameters. We investigate the bitwidth necessary for effective training and gain preliminary insights into the relationship between architecture and its learning ability. • Adaptive Precision Training (APT) trains a quantised network without a master copy. • APT saves 60-72.5% memory for model parameter in training with limited accuracy loss. • Insights into the characteristics of building blocks in neural network architectures. [ABSTRACT FROM AUTHOR]

Optimization and control of wastewater treatment process (WTP) can contribute to cost reduction and efficiency. A wastewater treatment process multi-objective optimization (WTPMO) framework is proposed in this paper to provide suggestions for decision-making in setting parameters of WTP. Firstly, the prediction models based on Extreme Gradient Boosting (XGB) with Bayesian optimization (BO) are developed for predicting effluent water quality (EQ) and energy consumption (EC) for different influent quality and process parameter settings. Then, the SHapley Additive exPlanations (SHAP) algorithm is used to complement the interpretability of machine learning to quantitatively evaluate the impact of different features on the predicted targets. Finally, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with the Technique for Ordering Preferences on Similarity of Ideal Solutions (TOPSIS) is introduced to solve and make decisions on the multi-objective optimization problem. The WTPMO applicability is validated on Benchmark Simulation Model 1 (BSM1). The results show that BOXGB achieves accurate prediction for EQ and EC with R2 values of 0.923 and 0.965, respectively, indicating that BO can effectively select the model hyperparameters in XGB. Based on SHAP supplemented the interpretability of the model to fully explain how the influent water quality and decision variables affect the EQ and EC of the WTP. In addition, the optimized process parameters are determined based on NSGA-II and TOPSIS, and the EC optimization rate is 1.552% while guaranteeing water quality compliance. Overall, this research can effectively achieve the optimization of WTP, ensure that the effluent water quality meets the standards while reducing energy consumption, assist Wastewater treatment plants (WWTPs) to achieve more intelligent and efficient operation and maintenance management, and provide strong support for environmental protection and sustainable development goals. [Display omitted] • Determining the hyperparameters of prediction models based on Bayesian optimization. • Providing insights into WTP based on interpretable machine learning. • Obtaining WTP optimization solution based on multi-objective evolutionary algorithm. • The proposed optimization framework can effectively reduce the EC and improve the EQ. [ABSTRACT FROM AUTHOR]

Flood modelling and forecasting can enhance our understanding of flood mechanisms and facilitate effective management of flood risk. Conventional flood hazard and risk assessments usually consider one driver at a time, whether it is ocean, fluvial or pluvial, without considering the compound nature of flood events. In this paper, we developed a novel approach for modelling and forecasting compound coastal-fluvial floods using a two-step framework. In step one, a hydrodynamic model is used to simulate floodwater propagation; while in step two, machine learning (ML) models are used to generate flood forecasts. The architecture of hydrodynamic-ML forecasting system incorporates a hydrodynamic model covering a specific domain, with individual ML models trained for each pixel. In total 7 ML models including: Support Vector Regression (SVR), Support Vector Machine (SVM), Radial Basis Function (RBF), Linear Regression (LR), Gaussian Process Regression (GPR), Decision Tree (DT), and Artificial Neural Network (ANN) were applied in this study. Forecasting compound floods is achieved using two sets of inputs: timeseries of river discharges in the upstream fluvial section and downstream ocean water levels in the coastal areas. The accuracy of the flood forecasting system is demonstrated for Cork City, Ireland; and modelling performance was evaluated using several statistical tools. Results show that the proposed models can provide reliable estimates of flood inundation and associated water depths. Overall, the RBF model exhibits the best performance. Despite the complexity of compound multi-driver floods, this study shows that the coupled hydrodynamic-ML approach can forecast coastal-fluvial flood with limited hydraulic and hydrological input data. This system overcomes the limitations of traditional hydrodynamic model-based systems where trade-offs between the always competing numerical model accuracy and computational time prohibit the model to be used for short-term flood forecasting. Once trained, the ML component of the coupled system can perform flood forecasting in near real-time, potentially integrating into a flood early warning system. Accurate flood forecasting has a wide range of positive societal impacts, including improved flood preparedness, increased confidence, better resource allocation, reduced flood damage, and potentially even flood prevention. • Novel technique to improve compound coastal-fluvial flood modelling. • Flood modelling technique based on seven Machine Learning methods. • Approach is successfully implemented, and results are evaluated over Cork, Ireland. • The results demonstrate minimal quantitative errors for the proposed models. [ABSTRACT FROM AUTHOR]

In recent years there has been increased use of machine learning (ML) techniques within mathematics, including symbolic computation where it may be applied safely to optimise or select algorithms. This paper explores whether using explainable AI (XAI) techniques on such ML models can offer new insight for symbolic computation, inspiring new implementations within computer algebra systems that do not directly call upon AI tools. We present a case study on the use of ML to select the variable ordering for cylindrical algebraic decomposition. It has already been demonstrated that ML can make the choice well, but here we show how the SHAP tool for explainability can be used to inform new heuristics of a size and complexity similar to those human-designed heuristics currently commonly used in symbolic computation. [ABSTRACT FROM AUTHOR]

• Integration of Explainable Artificial Intelligence (XAI) models on fiber optic SPR sensors. • Insights into the intricate patterns and features learned by the model are attained. • A comparative analysis of XAI models, namely SHAP and LIME is carried out. • LIME and SHAP methods jointly find that metal layer thickness has considerably greater influence than wavelength on sensing performance. • This finding is consistent with the concept of radiation damping related to fiber optic SPR sensor. In recent years, there has been a significant surge in interest surrounding the utilization of machine learning techniques to optimize the performance of fiber optic sensors. This paper delves into the integration of machine learning methodologies, with a specific focus on Explainable Artificial Intelligence (XAI) models, within the domain of fiber optic surface plasmon resonance (SPR) sensors. We implement XAI techniques into a previously-trained Gaussian Process Regression (GPR) model to gain insights into the intricate patterns and features learned by the model, thereby providing valuable insights into its decision-making process. Furthermore, we present a comparative analysis of XAI models, namely SHAP and LIME , to elucidate the individual impact of light wavelength (λ) and metal layer thickness (d m) on the enhancement of sensor's figure of merit (FOM). The results obtained from both LIME and SHAP methods lead to a common finding that compared to λ, it is the value of d m that possesses a significantly greater influence on achieving maximum FOM. Furthermore, this finding is in complete agreement with the concept of radiation damping related to fiber optic SPR sensor structures. This study has the potential to contribute to the refinement of design and fabrication processes related to fiber optic SPR sensor for a wide variety of applications. [ABSTRACT FROM AUTHOR]

Online learning is an efficient approach in machine learning and statistics, which iteratively updates models upon the observation of a sequence of training examples. A representative online learning algorithm is the online gradient descent, which has found wide applications due to its low complexity and scalability to large datasets. Kernel-based learning methods have been proven to be quite successful in dealing with nonlinearity in the data and multivariate optimization. In this paper we present a class of kernel-based online gradient descent algorithm for addressing regression problems, which generates sparse estimators in an iterative way to reduce the algorithmic complexity for training streaming datasets and model selection in large-scale learning scenarios. In the setting of support vector regression (SVR), we design the sparse online learning algorithm by introducing a sequence of insensitive distance-based loss functions. We prove consistency and error bounds quantifying the generalization performance of such algorithms under mild conditions. The theoretical results demonstrate the interplay between statistical accuracy and sparsity property during learning processes. We show that the insensitive parameter plays a crucial role in providing sparsity as well as fast convergence rates. The numerical experiments also support our theoretical results. [ABSTRACT FROM AUTHOR]

This paper examines the impact of changes in the stringency of environmental regulations on productivity growth. We exploit several data sources, including the OECD Environmental Policy Stringency Index and balance sheet information from ORBIS and iBACH, to test the Porter hypothesis, according to which firms' productivity can benefit from more stringent environmental policies. We estimate the regulatory impact over a five-year horizon using panel local projections. To identify the direction of the effects, we estimate CO 2 equivalent emissions for all firms in our sample using a machine learning algorithm. As suggested by the country-level analysis and confirmed by the firm-level analysis, policy tightening negatively affects productivity growth of high-polluting firms and to a larger extent than that of their low-polluting peers. Hence, we do not find support for the Porter hypothesis in general. However, not all policies have the same impact – non-market based policies are the most detrimental to productivity growth – and not all highly polluting firms are affected in the same way – the negative impact is mitigated for large firms, which may benefit from easier access to finance and greater innovativeness. [ABSTRACT FROM AUTHOR]

This paper proposes a mesh-free computational framework and machine learning theory for solving elliptic PDEs on unknown manifolds, identified with point clouds, based on diffusion maps (DM) and deep learning. The PDE solver is formulated as a supervised learning task to solve a least-squares regression problem that imposes an algebraic equation approximating a PDE (and boundary conditions if applicable). This algebraic equation involves a graph-Laplacian type matrix obtained via DM asymptotic expansion, which is a consistent estimator of second-order elliptic differential operators. The resulting numerical method is to solve a highly non-convex empirical risk minimization problem subjected to a solution from a hypothesis space of neural networks (NNs). In a well-posed elliptic PDE setting, when the hypothesis space consists of neural networks with either infinite width or depth, we show that the global minimizer of the empirical loss function is a consistent solution in the limit of large training data. When the hypothesis space is a two-layer neural network, we show that for a sufficiently large width, gradient descent can identify a global minimizer of the empirical loss function. Supporting numerical examples demonstrate the convergence of the solutions, ranging from simple manifolds with low and high co-dimensions, to rough surfaces with and without boundaries. We also show that the proposed NN solver can robustly generalize the PDE solution on new data points with generalization errors that are almost identical to the training errors, superseding a Nyström-based interpolation method. [ABSTRACT FROM AUTHOR]

Life cycle assessment (LCA) plays a crucial role in green manufacturing to uncover the critical aspects for alleviating the environmental burdens due to manufacturing processes. However, the scarcity of life cycle inventory (LCI) data for the manufacturing processes is a considerable challenge. This paper proposes a novel approach to extrapolate LCI data of manufacturing processes. Taking advantage of LCI data in the Ecoinvent datasets, decision tree-based supervised machine learning models, namely decision tree, random forest, gradient boosting, and adaptive boosting, have been developed to extrapolate the data of GHG emissions, i.e., carbon dioxide, nitrous oxide, methane, and water vapor. Initially, a correlation analysis was conducted to derive the most influential factors on GHG quantities resulting from manufacturing activities. First, the collected data have been preprocessed and split into train and test sets (70% and 30%, respectively). Second, a five-fold cross-validation method was applied to tune the hyperparameters of the models. Then, the models were re-trained using the best hyperparameters and evaluated using the test set. The results reveal that the Gradient Boosting model has a superior predictive performance for extrapolating the GHG emission data, with average coefficients of determination (R 2) on the test set <0.95. Moreover, the model predictions involve relatively low values of the average root mean squared error and an average mean percentage of error on the test set. The correlation and feature importance analyses emphasized that the workpiece material and manufacturing technology have a considerable effect on natural resource consumption, i.e., energy, material, and water inflows into the process. Meanwhile, energy consumption, water usage, and raw aluminum depletion were the most influential factors in GHG emissions. Eventually, a case study to extrapolate the inflows and the outflows for new manufacturing activities has been conducted using the validated models. The proposed GraBoost model provides a computational supplementary approach to estimate and extrapolate the GHG emissions for different manufacturing processes when LCI data are incomplete or don't exist within LCI databases. • Extrapolation of LCI data using decision tree-based machine learning models. • Filling some gaps for manufacturing process LCI data. • Gradient Boosting model can bridge and extrapolate greenhouse gas emissions for new manufacturing activities. [ABSTRACT FROM AUTHOR]

With the promise of higher throughput, and better response times, 6G networks provide a significant enabler for smart cities to evolve. The rapidly-growing reliance on connected devices within the smart city context encourages malicious actors to target these devices to achieve various malicious goals. In this paper, we present a novel defense technique that creates a cloud-based virtualized honeypot/twin that is designed to receive malicious traffic through edge-based machine learning-enabled detection system. The proposed system performs early identification of malicious traffic in a software defined network-enabled edge routing point to divert that traffic away from the 6G-enabled smart city endpoints. Testing of the proposed system showed an accuracy exceeding 99.8%, with an F 1 score of 0.9984. [ABSTRACT FROM AUTHOR]

DNA 4 mC plays a crucial role in the genetic expression process of organisms. However, existing deep learning algorithms have shortcomings in the ability to represent DNA sequence features. In this paper, we propose a 4 mC site identification algorithm, DNABert-4mC, based on a fusion of the pruned pre-training DNABert-Pruning model and artificial feature encoding to identify 4 mC sites. The algorithm prunes and compresses the DNABert model, resulting in the pruned pre-training model DNABert-Pruning. This model reduces the number of parameters and removes redundancy from output features, yielding more precise feature representations while upholding accuracy.Simultaneously, the algorithm constructs an artificial feature encoding module to assist the DNABert-Pruning model in feature representation, effectively supplementing the information that is missing from the pre-trained features. The algorithm also introduces the AFF-4mC fusion strategy, which combines artificial feature encoding with the DNABert-Pruning model, to improve the feature representation capability of DNA sequences in multi-semantic spaces and better extract 4 mC sites and the distribution of nucleotide importance within the sequence. In experiments on six independent test sets, the DNABert-4mC algorithm achieved an average AUC value of 93.81%, outperforming seven other advanced algorithms with improvements of 2.05%, 5.02%, 11.32%, 5.90%, 12.02%, 2.42% and 2.34%, respectively. [Display omitted] • Train a new pruning pretraining model on DNA sequences to extract feature information. • The introduction of manually assisted features has expanded the search space for sequence feature. • Attention fusion strategy better promotes the fusion output of features from different dimensions. • The complementary nature of machine features and manual features better fits the target features. [ABSTRACT FROM AUTHOR]

Detecting anomalies in the vibrational features of age-old buildings is crucial within the Structural Health Monitoring (SHM) framework. The SHM techniques can leverage information from onsite measurements and environmental sources to identify the dynamic properties (such as the frequencies) of the monitored structure, searching for possible deviations or unusual behavior over time. The Temporal Fusion Transformer (TFT) network is a deep learning algorithm designed for multi-horizon time series forecasting and initially tested on electricity, traffic, retail, and volatility problems. In this paper, it is applied to SHM. More precisely, the TFT approach is adopted to investigate the behavior of the Guinigi Tower located in Lucca (Italy) and subjected to a long-term dynamic monitoring campaign. The TFT network is trained on the tower's experimental frequencies enriched with other environmental parameters. The transformer is then employed to predict the vibrational features (natural frequencies, root mean squares values of the velocity time series) and detect possible anomalies or unexpected events by inspecting how much the actual frequencies deviate from the predicted ones. The TFT technique is used to detect the effects of the Viareggio earthquake that occurred on 6 February 2022, and the structural damage induced by three simulated damage scenarios. [ABSTRACT FROM AUTHOR]