Search

Picking protein particles in cryo-electron microscopy (cryo-EM) micrographs is a crucial step in the cryo-EM-based structure determination. However, existing methods trained on a limited amount of cryo-EM data still cannot accurately pick protein particles from noisy cryo-EM images. The general foundational artificial intelligence–based image segmentation model such as Meta's Segment Anything Model (SAM) cannot segment protein particles well because their training data do not include cryo-EM images. Here, we present a novel approach (CryoSegNet) of integrating an attention-gated U-shape network (U-Net) specially designed and trained for cryo-EM particle picking and the SAM. The U-Net is first trained on a large cryo-EM image dataset and then used to generate input from original cryo-EM images for SAM to make particle pickings. CryoSegNet shows both high precision and recall in segmenting protein particles from cryo-EM micrographs, irrespective of protein type, shape and size. On several independent datasets of various protein types, CryoSegNet outperforms two top machine learning particle pickers crYOLO and Topaz as well as SAM itself. The average resolution of density maps reconstructed from the particles picked by CryoSegNet is 3.33 Å, 7% better than 3.58 Å of Topaz and 14% better than 3.87 Å of crYOLO. It is publicly available at https://github.com/jianlin-cheng/CryoSegNet [ABSTRACT FROM AUTHOR]

Data discretisation focuses on converting continuous attribute values to discrete ones which are closer to a knowledge-level representation that is easier to understand, use, and explain than continuous values. On the other hand, instance selection aims at filtering out noisy or unrepresentative data samples from a given training dataset before constructing a learning model. In practice, some domain datasets may require processing with both discretisation and instance selection at the same time. In such cases, the order in which discretisation and instance selection are combined will result in differences in the processed datasets. For example, discretisation can be performed first based on the original dataset, after which the instance selection algorithm is used to evaluate the discrete type of data for selection, whereas the alternative is to perform instance selection first based on the continuous type of data, then using the discretiser to transfer the attribute type of values of a reduced dataset. However, this issue has not been investigated before. The aim of this paper is to compare the performance of a classifier trained and tested over datasets processed by these combination orders. Specifically, the minimum description length principle (MDLP) and ChiMerge are used for discretisation, and IB3, DROP3 and GA for instance selection. The experimental results obtained using ten different domain datasets show that executing instance selection first and discretisation second perform the best, which can be used as the guideline for the datasets that require performing both steps. In particular, combining DROP3 and MDLP can provide classification accuracy of 0.85 and AUC of 0.8, which can be regarded as the representative baseline for future related researches. [ABSTRACT FROM AUTHOR]

The International Journal of Information Technology & Decision Making has published its fourth issue, featuring 10 original papers from distinguished authors in eight countries. The papers cover a range of topics, including deep learning for malaria detection, social banking, multi-attribute decision-making, video event detection, ERP system evaluation, COVID-19 vaccine analysis, order picking systems, big data analytics in central banking, and estimation of missing entries in preference matrices. The articles provide valuable insights and innovative solutions in the field of information technology and decision making. [Extracted from the article]

Summary: Background: The precise estimation of cases with significant fibrosis (SF) is an unmet goal in non‐alcoholic fatty liver disease (NAFLD/MASLD). Aims: We evaluated the performance of machine learning (ML) and non‐patented scores for ruling out SF among NAFLD/MASLD patients. Methods: Twenty‐one ML models were trained (N = 1153), tested (N = 283), and validated (N = 220) on clinical and biochemical parameters of histologically‐proven NAFLD/MASLD patients (N = 1656) collected across 14 centres in 8 Asian countries. Their performance for detecting histological‐SF (≥F2fibrosis) were evaluated with APRI, FIB4, NFS, BARD, and SAFE (NPV/F1‐score as model‐selection criteria). Results: Patients aged 47 years (median), 54.6% males, 73.7% with metabolic syndrome, and 32.9% with histological‐SF were included in the study. Patients with SFvs.no‐SF had higher age, aminotransferases, fasting plasma glucose, metabolic syndrome, uncontrolled diabetes, and NAFLD activity score (p < 0.001, each). ML models showed 7%–12% better discrimination than FIB‐4 to detect SF. Optimised random forest (RF) yielded best NPV/F1 in overall set (0.947/0.754), test set (0.798/0.588) and validation set (0.852/0.559), as compared to FIB4 in overall set (0.744/0.499), test set (0.722/0.456), and validation set (0.806/0.507). Compared to FIB‐4, RF could pick 10 times more patients with SF, reduce unnecessary referrals by 28%, and prevent missed referrals by 78%. Age, AST, ALT fasting plasma glucose, and platelet count were top features determining the SF. Sequential use of SAFE < 140 and FIB4 < 1.2 (when SAFE > 140) was next best in ruling out SF (NPV of 0.757, 0.724 and 0.827 in overall, test and validation set). Conclusions: ML with clinical, anthropometric data and simple blood investigations perform better than FIB‐4 for ruling out SF in biopsy‐proven Asian NAFLD/MASLD patients. [ABSTRACT FROM AUTHOR]

Motivation Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of large protein complexes. Picking single protein particles from cryo-EM micrographs (images) is a crucial step in reconstructing protein structures from them. However, the widely used template-based particle picking process requires some manual particle picking and is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) can potentially automate particle picking, the current AI methods pick particles with low precision or low recall. The erroneously picked particles can severely reduce the quality of reconstructed protein structures, especially for the micrographs with low signal-to-noise ratio. Results To address these shortcomings, we devised CryoTransformer based on transformers, residual networks, and image processing techniques to accurately pick protein particles from cryo-EM micrographs. CryoTransformer was trained and tested on the largest labeled cryo-EM protein particle dataset—CryoPPP. It outperforms the current state-of-the-art machine learning methods of particle picking in terms of the resolution of 3D density maps reconstructed from the picked particles as well as F1-score, and is poised to facilitate the automation of the cryo-EM protein particle picking. Availability and implementation The source code and data for CryoTransformer are openly available at: https://github.com/jianlin-cheng/CryoTransformer. [ABSTRACT FROM AUTHOR]

Conical pick cutters are by far the most common type of rock cutting tools used on variety of excavation equipment in mining and civil applications. Prediction of the forces acting on pick cutters when cutting rock can be an important input towards cutterhead design and performance estimation for such equipment. The cutting forces are a function of the rock strength and pick tip geometry, which is impacted by the bit wear. To develop a prediction model, a database of mean cutting force (MCF) measured in full-scale testing has been compiled and subsequently analyzed using regression methods to find the empirical equations linking MCF to the bit, cutting geometry and rock properties. Full-scale cutting tests are known to offer precise measurement of the cutting forces for a given bit geometry, cutting geometry (spacing between the cuts and depth of penetration), and combined rock mechanic characteristics of the sample; consequently, the information can be used to develop models of prediction of cutting forces. Linear and log-linear regression and tree-based machine learning models (random forest, decision tree, and extreme gradient boost) were used for the analysis of the experimental data. The results demonstrated that while using input parameters including uniaxial compressive strength (UCS), spacing, Brazilian tensile strength (BTS), penetration, and pick cutter's tip radius and tip angle, models can offer a reasonable prediction of the cutting forces. Among the models that have been examined, regression tree models, especially extreme gradient boost shows the highest coefficient of determination (R2), and the lowest mean absolute error (MAE). Highlights: The key input parameters that affect MCF are recognized, and their influence on MCF is thoroughly examined. The most important parameters for predicting cutting forces are UCS, tip angle, penetration, and BTS. Tree-based machine learning models demonstrate superior performance in predicting MCF. [ABSTRACT FROM AUTHOR]

With advancements in both the quality and collection speed of magnetic data captured by uncrewed aerial vehicle (UAV)-based systems, there is a growing need for robust and efficient systems to automatically interpret such data. Many existing conventional methods require manual inspection of the survey data to pick out candidate areas for further analysis. We automate this initial process by implementing unsupervised machine learning techniques to identify small, well-defined regions. When further analysis is conducted with magnetic inversion algorithms, then our approach also reduces the nonlinear computation and time costs by breaking one huge inversion problem into several smaller ones. We also demonstrate robustness to noise and sidestep the requirement for large quantities of labeled training data: two pitfalls of current automation approaches. We propose first to use hierarchical clustering on filtered magnetic gradient data and then to fit ellipses to the resulting clusters to identify subregions for further analysis. In synthetic data experiments and on real-world datasets, our model successfully captures all true targets while simultaneously proposing fewer computationally costly false positives. With this approach, we take an important step towards fully automating the detection of high-risk subregions, but we wish to emphasize the importance of prudent skepticism until it has been tested and proven on more diverse data. [ABSTRACT FROM AUTHOR]

Warehouse design and planning involve complex decisions on receiving, storage, order picking and shipping products (i.e., stock-keeping units - SKUs) and can affect the performance of entire supply chains. With the advancement of Industry 4.0 and increased data availability, high-computing power, and ample storage capacity, Machine Learning (ML) has become an appealing technology to address warehouse planning challenges such as Storage Location Assignment Problems (SLAP) and Order Picking Problems (OPP) for intelligent warehousing management. This paper presents a state-of-the-art review of ML applied to Warehouse Management Systems (WMS) through the analysis of recent research application articles. A mapping to classify the scientific literature in this new research area, including ML methods, algorithms, data sources and use cases of ML-aided WMS, as well as further research perspectives and challenges, are introduced. Preliminary results suggest that the possible research areas in ML-WMS are still incipient and need to be further explored. [ABSTRACT FROM AUTHOR]

An accurate and trustworthy first break picking plays a key role in static correction calculations, velocity analysis, and deconvolution. First break traveltimes picking accuracy ensures correct and reliable seismic data processing results. Many methods are available to perform the first break pickings automatically. Most of these methods, however, are not robust when there is a low signal‐to‐noise ratio (SNR). In this study, to automatically determine the traveltimes of the first arrivals, we used the density‐based spatial clustering application with noise (DBSCAN) and the super‐virtual refraction interferometry (SVI). In the case of noisy data, using only DBSCAN for first break picking shows poor accuracy. To deal with this issue, SVI is employed to improve the SNR of the data, and then DBSCAN is applied again to the enhanced data for accurate picking. In the first step, DBSCAN is used to define a muting window for SVI. In the second step, SVI is employed to improve the first arrival SNR. In the third step, DBSCAN is applied to determine the final first arrival traveltime. The proposed approach is tested on synthetic and field data sets, where the manual and the cross‐correlation pickings are compared to the DBSCAN automatic pickings. We further test the proposed approach on a publicly available data set to benchmark our technique for first‐break accuracy with other established methods. Results show that the first arrival traveltime picks using the proposed approach are very accurate compared to manual picking. Plain Language Summary: Recorded seismic data goes through many processing steps to get a final image of the subsurface. One of the important processing steps is first break traveltime picking. Its accuracy is very important for accurate data processing outcomes. Many methods struggle to make an accurate automatic first break traveltime picking when the data is polluted with noise. In this research work, we used an unsupervised machine learning technique to perform automatic first break traveltime picking which produced good results even in the case of noisy data. The performance of the machine learning algorithm is improved by enhancing the signal‐to‐noise ratio of the data because of using the super‐virtual refraction interferometry (SVI) technique. The proposed methodology is tested using synthetic and field examples, and results show a better picking of the first breaks after using SVI as part of the working flowchart. Key Points: An unsupervised machine learning algorithm, the density‐based spatial clustering application with noise (DBSCAN), is used to automatically pick the first arrival traveltime of recorded seismic dataSuper‐virtual refraction interferometry is used to enhance signal‐to‐noise ratio of far‐offset traces then DBSCAN is used to pick the first breaks automatically and accurately [ABSTRACT FROM AUTHOR]

Recently, few methods for understanding machine learning model's outputs have been developed. SHAP and LIME are two well-known examples of these methods. They provide individual explanations based on feature importance for each instance. While remarkable scores have been achieved for individual explanations, understanding the model's decisions globally remains a complex task. Methods like LIME were extended to face this complexity by using individual explanations. In this approach, the problem was expressed as a submodular optimization problem. This algorithm is a bottom-up method aiming at providing a global explanation. It consists of picking a group of individual explanations which illustrate the global behavior of the model and avoid redundancy. In this paper, we propose CoSP (Co-Selection Pick) framework that allows a global explainability of any black-box model by selecting individual explanations based on a similarity preserving approach. Unlike submodular optimization, in our method the problem is considered as a co-selection task. This approach achieves a co-selection of instances and features over the explanations provided by any explainer. The proposed framework is more generic given that it is possible to make the co-selection either in supervised or unsupervised scenarios and also over explanations provided by any local explainer. Preliminary experimental results are made to validate our proposal. [ABSTRACT FROM AUTHOR]

Estimates of the onset times of P phases from active source experiments can effectively be used in developing wavespeed models, and the large number of recordings typical of such experiments incentivizes the development of automated approaches to generate these estimates. The simplicity and repeatability of an airgun source such as that used in the 2016 Pisagua/Iquique Crustal Tomography to Understand the Region of the Earthquake Source (PICTURES) project in northern Chile suggested that a straightforward application of waveform cross-correlation would suffice for arrivals recorded by a network of inland seismic stations, but did not work well due to significant variations in waveform morphology. For similar reasons, the machine learning application PhaseNet also did not work well. Application of an alternative algorithm typically used in passive source investigations that is indifferent to waveform morphology, the Regressive ESTimator (REST) autopicking package, also proved unsatisfactory, largely because the limited spectral bandwidth of the airgun source and the frequent occurrence of local seismicity led to numerous false picks. This motivated the development of a new approach, named CORREL, that is a hybrid of REST and cross-correlation, with the addition of a constraint in the form of a polynomial function based on the REST picks that provides a reasonable prediction of an onset time. Compared to the results obtained originally from REST and simple waveform correlation, the application of CORREL to the PICTURES data both significantly increased the number of arrivals estimated and greatly reduced the number of outliers. The combination of techniques retains the precision afforded by cross correlation while taking advantage of the accuracy afforded by absolute time picking. The predictive polynomial also provides CORREL a better means to discriminate true shots from the abundant natural seismicity. [ABSTRACT FROM AUTHOR]

The development of automated segmentation and quantitative characterization of microtextured regions (MTRs) from the complex heterogeneous microstructures is urgently needed, since MTRs have been proven to be the critical issue that dominates the dwell-fatigue performance of aerospace components. In addition, MTRs in Ti alloys have similarities to microstructures encountered in other materials, including minerals and biomaterials. Meanwhile, machine learning (ML) offers new opportunities. This paper addresses segmentation and quantitative characterization of MTRs, where an ML approach, the Gaussian mixture models (GMMs) coupled with density-based spatial clustering of applications with noise (DBSCAN) clustering algorithms, was employed in order to process the orientation data acquired via EBSD in the Matlab environment. Pixels with orientation information acquired through electron backscatter diffraction (EBSD) are divided and colored into several "classes" (MTRs) within the defined c-axis misorientations (i.e., 25°, 20°, 15°, 10°, and 5°), the precision and efficacy of which are verified by the morphology and pole figure of the segmented MTR. An appropriate range of c-axis misorientations for MTR segmentation was derived, i.e., 15~20°. The contribution of this innovative technique is compared with previous studies. At the same time, the MTRs were statistically characterized in the global region. [ABSTRACT FROM AUTHOR]

The use of simulation and reinforcement learning can be viewed as a flexible approach to aid managerial decision-making, particularly in the face of growing complexity in manufacturing and logistic systems. Efficient supply chains heavily rely on steamlined warehouse operations, and therefore, having a well-informed storage location assignment policy is crucial for their improvement. The traditional methods found in the literature for tackling the storage location assignment problem have certain drawbacks, including the omission of stochastic process variability or the neglect of interaction between various warehouse workers. In this context, we explore the possibilities of combining simulation with reinforcement learning to develop effective mechanisms that allow for the quick acquisition of information about a complex environment, the processing of that information, and then the decision-making about the best storage location assignment. In order to test these concepts, we will make use of the FlexSim commercial simulator. [ABSTRACT FROM AUTHOR]

Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of biological macromolecular complexes. Picking single-protein particles from cryo-EM micrographs is a crucial step in reconstructing protein structures. However, the widely used template-based particle picking process is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) based particle picking can potentially automate the process, its development is hindered by lack of large, high-quality labelled training data. To address this bottleneck, we present CryoPPP, a large, diverse, expert-curated cryo-EM image dataset for protein particle picking and analysis. It consists of labelled cryo-EM micrographs (images) of 34 representative protein datasets selected from the Electron Microscopy Public Image Archive (EMPIAR). The dataset is 2.6 terabytes and includes 9,893 high-resolution micrographs with labelled protein particle coordinates. The labelling process was rigorously validated through 2D particle class validation and 3D density map validation with the gold standard. The dataset is expected to greatly facilitate the development of both AI and classical methods for automated cryo-EM protein particle picking. [ABSTRACT FROM AUTHOR]

The engineering project warehouse can combine various sensor devices and smart devices under the Internet of Things technology to realize the convenient management of the warehouse. The Internet of Things technology combined with the machine learning model can make various industries transform to intelligence. The use of IoT technology and machine learning models for warehouse management can achieve an unattended warehouse effect. The Internet of Things has gradually developed into the intelligent technology that attracts the most attention in various industries with the advancement of electronic components required by various sensors. Combining various sensor devices and smart devices under the Internet of Things technology to achieve convenient management of warehouses, its intelligent management of warehouse security, environment, fire protection, energy consumption, etc. can save a lot of manpower and material resources, and improve the project warehouse, Utilization of supplies. Machine learning technology is a new type of computer self-learning technology produced along with artificial intelligence technology, which can combine the corresponding algorithm and the definition of the developer to realize the learning of the defined transaction. Because the way of this operation is similar to the human learning ability, machine learning Warehouse management for engineering projects will maximize the unattended effect of the warehouse. The research adopts a combination of questionnaire survey and modeling analysis. At first, analyzes the current demand points of engineering project warehouse management in various industries through a questionnaire survey, and designs the Internet of Things auxiliary scheme for engineering project warehouse management according to the demand points. The IoT-assisted machine learning model compares the IoT engineering project warehouse management solution without machine learning model with the IoT engineering project warehouse management solution with machine learning. It is found that the solution with machine learning model can effectively improve the engineering project warehouse management. abilities in all aspects including the effective utilization rate of necessities, manpower saving and safety accident control, which proves that the research has high use value. [ABSTRACT FROM AUTHOR]

During excavation of roadheader, specific energy (SE) is a key component of rock cuttability evaluation and cutting head design. Previous studies have shown that the specific energy is simultaneously affected by physical and mechanical parameters of rock, pick geometry, and pick operation parameters. In the paper, six machine learning (ML) algorithms (back-propagation neural network, Elman neural network, extreme learning machine, kernel extreme learning machine, random forest, support vector regression) optimized by sparrow search algorithm (SSA) for SE prediction are developed by simultaneously considering two rock mechanical parameters (tensile strength of the rock σt and uniaxial compressive strength of the rock σc), one pick geometry (cone angle θ) and five pick operation parameters (cutting depth d, tool spacing s, rake angle α, attack angle γ, back-clearance angle β). 213 rock samples containing 26 rock types were selected to build the SSA-ML model. Mean absolute error (MAE), mean absolute percentage error (MAPE) and determination coefficient (R2) between the measured and predicted values are assigned as evaluation indicators to compare prediction performance of SSA-ML models. The importance of input variables is calculated internally using random forest (RF) algorithm. The results indicated that SSA-RF model with MAE of (0.7938 and 1.0438), MAPE of (12.76% and 16.98%), R2 of (0.9632 and 0.8943) on the training set and testing set has the most potential for SE prediction. The sensitive analysis shows the d, σc and σt are the most significant input variables for SE prediction. [ABSTRACT FROM AUTHOR]

Data scientists require rich mental models of how AI systems behave to effectively train, debug, and work with them. Despite the prevalence of AI analysis tools, there is no general theory describing how people make sense of what their models have learned. We frame this process as a form of sensemaking and derive a framework describing how data scientists develop mental models of AI behavior. To evaluate the framework, we show how existing AI analysis tools fit into this sensemaking process and use it to design AIFinnity, a system for analyzing image-and-text models. Lastly, we explored how data scientists use a tool developed with the framework through a think-aloud study with 10 data scientists tasked with using AIFinnity to pick an image captioning model. We found that AIFinnity’s sensemaking workflow reflected participants’ mental processes and enabled them to discover and validate diverse AI behaviors. [ABSTRACT FROM AUTHOR]

In the rapidly evolving landscape of e-commerce, the need for personalized experiences and real-time adaptation has become paramount. This article proposes a framework for adaptive microservices in the e-commerce domain, leveraging machine learning techniques and real-time adaptation to enhance user experiences and drive business growth. The framework suggests implementing each e-commerce activity as an independent microservice, enabling modular development, scalability, and flexibility. Key microservices such as product catalog management, shopping cart management, order processing, and user management are identified and integrated into an architecture that fosters seamless communication and data exchange. To enable self-adaptation and personalization, a Monitor-Analyze-Plan-Execute (MAPE) loop is introduced. The monitoring phase involves integrating additional services to collect relevant data, including user interactions, search keywords, session data, and feedback. This data is leveraged in the analysis phase, where machine learning techniques are employed to preprocess and extract meaningful insights. Cosine similarity is utilized to calculate similarity scores between user preferences and available products, enabling the generation of personalized recommendations. The proposed approach focuses on connecting the product management microservice to a self-adaptive mechanism, ensuring that the existing infrastructure remains largely untouched. This enables companies to enhance their e-commerce platforms without undergoing significant overhauls or disruptions. Another advantage lies in the flexibility and scalability offered by the modular microservices architecture. Companies can selectively integrate the self-adaptive mechanism into the product management microservice, maintaining the autonomy and independence of other microservices. This flexibility facilitates scalability as businesses expand and encounter growing demands. [ABSTRACT FROM AUTHOR]

Autonomous capabilities are required in AmI environments in order to adapt systems to new environmental conditions and situations. However, keeping the human in the loop and in control of such systems is still necessary because of the diversity of systems, domains, environments, context situations, and social and legal constraints, which makes full autonomy a utopia within the short or medium term. Human-system integration introduces an important number of challenges and problems that have to be solved. On the one hand, humans should interact with systems even in those situations where their attentional, cognitive, and physical resources are limited in order to perform the interaction. On the other hand, systems must avoid overwhelming the user with unnecessary actions. Therefore, appropriate user-centered methods for AmI development should be used to help designers analyze and design human-in-the-loop interactions in AmI environments. This paper presents a user-centered design method that defines a process with a set of tools and techniques that supports the process steps in order to systematically design, prototype, and validate human-in-the-loop (HiL) solutions. The process starts with the definition of the HiL design, which defines how the system cooperates with the human. This HiL design is built using a conceptual framework that focuses on achieving human-system interactions that get human attention and avoid obtrusiveness. Then, we provide a software infrastructure to generate a prototype based on the HiL design and validate it by having end-users use a web simulator. The feedback data generated during the prototype user validation is gathered and used by a machine learning tool that infers the user's needs and preferences. Finally, these inferences are used to automatically enhance the human-in-the-loop designs and prototypes. We have validated the proposed method through a twofold perspective: an experiment to analyze the perception of interaction designers regarding their acceptance of the design method and another experiment to evaluate the usefulness of the "smart" prototyping technique. The results obtained point out the acceptability of the proposed method by designers and the useful adaptations provided by the "smart" prototyping technique to achieve a HiL design that adapts well to users' preferences and needs. [ABSTRACT FROM AUTHOR]

In order to process speech, most state-of-the-art experimental methods employ convolutional neural networks (CNNs), which operate on a continuous, 1-dimensional (1-D) time stream. In an audio signal, the mel-spectrogram facilitates the representation of attributes of the utterances' in the frequency domain (which corresponds to the speech spectrum). Moreover, for a time-series speaker signal, CNNs are superior to machine or transfer learning models in capturing characteristics from long-form talks. This paper introduces a jump-connected 1-D CNN that employs a combined loss function for speaker recognition. The suggested model uses a 1-D convolutional layer combined with jump connections to extract speaker-specific characteristics; this reduces time-based and frequency-based variability for faster computing. A combined softmax loss, stable L2-norm, and smooth L1-norm loss function guide the proposed compact convolutional neural networks (CCNN) to identify the correct spokesman with improved efficacy. We evaluated the proposed framework using various standard and real-time audio datasets. The experimental findings demonstrate that the proposed CCNN outperforms existing approaches by reducing the equal error rate by 9.02 %. Also, our recommended voiceprint identification model achieves an impressive average speaker recognition rate of 98.76 %. Simultaneously, the reliability of the 1-D CCNN is tested under various conditions. Other fields of study, like language modelling, could employ this approach after some fine-tuning. Relevance of the work: Speaker recognition is an area of interest in which machine learning (ML) and deep learning (DL) schemes, when combined, have the potential to make history in the areas of forensic sciences, automation, and authentication. Using a modest CNN can enhance the identification and verification process by ignoring many issues such as false positives, background noise, and so on. Expanding this process would facilitate raga identification and disease treatment therapies. [ABSTRACT FROM AUTHOR]

We developed a high-resolution machine learning based surrogate model to identify a robust land-use future for Australia which meets multiple UN Sustainable Development Goals. We compared machine learning models with different architectures to pick the best performing model considering the data type, accuracy metrics, ability to handle uncertainty and computational overhead requirement. The surrogate model, called ML-LUTO Spatial , was trained on the Land-Use Trade-Offs (version 1.0) model of Australian agricultural land system sustainability. Using the surrogate model, we generated projections of land-use futures at 1.1 km resolution with 95% classification accuracy, and which far surpassed the computational benchmarks of the original model. This efficiency enabled the generation of numerous SDG-compliant (SDGs 2, 6, 7, 13, 15) future land-use maps on a standard laptop, a task previously dependent upon high-performance computing clusters. Combining these projections, we derived a single, robust land-use future and quantified the uncertainty. Our findings indicate that while agricultural land-use remains dominant in all Australian regions, extensive carbon plantings were identified in Queensland and environmental plantings played a role across the study area, reflecting a growing urgency for offsetting greenhouse gas emissions and the restoration of ecosystems to support biodiversity across Australia to meet the 2050 Sustainable Development Goals. • ML-LUTO-Spatial machine learning surrogate model of Land-Use Trade-Offs model. • Able to produce future land-use projections with 95% accuracy. • Quick to train and test with basic laptop computer to help decision support. • Robust land-use pathways produced for Australia for meeting SDG targets. [ABSTRACT FROM AUTHOR]

The CIDOC Conceptual Reference Model (CIDOC-CRM) is an ISO Standard ontology for the cultural domain that is used for enabling semantic interoperability between museums, libraries, archives and other cultural institutions. For leveraging CIDOC-CRM, several processes and tasks have to be carried out. It is therefore important to investigate to what extent we can automate these processes in order to facilitate interoperability. For this reason, in this paper, we describe the related tasks, and we survey recent works that apply machine learning (ML) techniques for reducing the costs related to CIDOC-CRM-based compliance and interoperability. In particular, we (a) analyze the main processes and tasks, (b) identify tasks where the recent advances of ML (including Deep Learning) would be beneficial, (c) identify cases where ML has been applied (and the results are successful/promising) and (d) suggest tasks that can benefit from applying ML. Finally, since the approaches that leverage both CIDOC-CRM data and ML are few in number, (e) we introduce our vision for the given topic, and (f) we provide a list of open CIDOC-CRM datasets that can be potentially used for ML tasks. [ABSTRACT FROM AUTHOR]

In semiconductor manufacturing processes, yield analysis aims to increase the yield by determining and managing the causes of low yield. The variable data collected from semiconductor manufacturing processes, in which hundreds of unit processes are implemented according to specific conditions and sequences, are interdependent, and the variables related to previous processes influence the variables in subsequent processes. Therefore, the order of processes should be considered when building a model that searches for the causes of low yield. However, there have been few studies in this area. This paper proposes a low-yield root cause search method considering the order of processes using a long short-term memory with attention mechanism (LSTM-AM) model. Specifically, the LSTM-AM model is applied to data classified according to the process structure of semiconductor products, and the causes of low yield are determined considering the order of processes by extracting attention weights. Experiments are conducted to verify the suitability of the proposed method using real yield data from a semiconductor company. The experimental results confirm that the proposed method outperforms the existing low yield root cause search methods in terms of low yield prediction. [ABSTRACT FROM AUTHOR]

In the order picking process of the warehouse center, considering the rapid increase in the volume of orders arriving at the picking center at the time of the promotional festival, a hybrid operation mode with multiple picking tables is used to meet the picking requirements of the huge number of real-time orders. Therefore, in this paper, a hybrid picking mode is proposed, taking into account both the idle degree of picking stations and their order item centers of gravity, and a new reinforcement learning algorithm embedding mechanism (PRL) with placeholder control is designed to solve the problem of a huge number of real-time item orders arriving at the picking center system on promotional holidays and in inconsistent quantities, and numerical simulations are performed for this algorithm. The experimental results show that the PRL algorithm in hybrid picking mode can handle a huge number of orders simultaneously and improve picking efficiency effectively. [ABSTRACT FROM AUTHOR]

The Kepler and Transiting Exoplanet Survey Satellite (TESS) missions have generated over 100,000 potential transit signals that must be processed in order to create a catalog of planet candidates. During the past few years, there has been a growing interest in using machine learning to analyze these data in search of new exoplanets. Different from the existing machine learning works, ExoMiner , the proposed deep learning classifier in this work, mimics how domain experts examine diagnostic tests to vet a transit signal. ExoMiner is a highly accurate, explainable, and robust classifier that (1) allows us to validate 301 new exoplanets from the MAST Kepler Archive and (2) is general enough to be applied across missions such as the ongoing TESS mission. We perform an extensive experimental study to verify that ExoMiner is more reliable and accurate than the existing transit signal classifiers in terms of different classification and ranking metrics. For example, for a fixed precision value of 99%, ExoMiner retrieves 93.6% of all exoplanets in the test set (i.e., recall = 0.936), while this rate is 76.3% for the best existing classifier. Furthermore, the modular design of ExoMiner favors its explainability. We introduce a simple explainability framework that provides experts with feedback on why ExoMiner classifies a transit signal into a specific class label (e.g., planet candidate or not planet candidate). [ABSTRACT FROM AUTHOR]

Machine learning (ML) is one of the most exciting fields of computing today. In the experimental evaluation, they showed that the new grammatical inference algorithm gives the best results in comparison to other automata or grammar learning methods as well as ML approach combining an unsupervised data-driven distributed representation and SVM. In [[11]], this problem is solved using several ML algorithms based on different student data including individual course grades and grade point averages. ML covers a wide range of learning algorithms, including classical ones such as linear regression, k-nearest neighbors, decision trees, support vector machines and neural networks, and newly developed algorithms such as deep learning and boosted tree models. [Extracted from the article]

With the intensification of market competition and the development of market globalization, the efficiency of supply chain management orders has become an important part of enterprise competition resources. The competition among enterprises is fierce. To achieve effective customer response quickly, the time for supply chain order management is minimized, and refine the order processing process. This article introduces the strategy research of supply chain management order based on a reinforcement learning algorithm. This article first combines the reinforcement learning algorithm and deep learning algorithm, using the optimal decision-making ability of reinforcement learning algorithm and deep learning algorithm. The combination of data perception and the optimal ability to analyze examine the data of the order process, order cycle, and order delivery process of the supply chain order management and give the optimal decision. The supply chain order management process conducts questionnaire surveys and seminars to understand the current process of supply chain order management and the problems derived from the analysis of data based on the deep learning algorithm. Finally, through the output of the optimal strategy of the reinforcement learning algorithm, the supply chain order management process was improved, and the satisfaction survey was conducted again. The survey showed that the satisfaction was improved, and the satisfaction reached more than 90%. [ABSTRACT FROM AUTHOR]

First arrival time picking is one of the critical processing steps of acoustic emission (AE)/microseismic (MS) monitoring for studying rock fracture processes. Because of massive monitoring data, the automatic arrival time picking technique is particularly desired. Inspired by recent successful applications of machine learning (ML) in earthquake phase identification, we propose a deep learning (DL)-based P-wave first arrival time picking method named AE Network (AEnet) for laboratory AE monitoring data. Our approach consists of two steps: classification and picking. The convolutional neural network (CNN) is used to classify each sample point of acoustic waveforms into either noise or signal. Different from prior DL-based phase picking studies using raw waveforms, we combine the waveform and high-order statistics as the input to enrich the input data features and accelerate the CNN model learning process. Our approach is examined using the laboratory AE monitoring data and the performance of each component of AEnet is also analyzed. The results show that the CNN model can classify the sample points accurately for the picking procedure. With this classification result, we pick the first arrival time of each trace using the curve fitting method and an unsupervised clustering algorithm. To evaluate the performance of AEnet, we apply Akaike Information Criterion-Short Term Averaging/Long Term Averaging Method (AIC-STA/LTA), one of the most popular and traditional picking methods, on the same waveforms and use the manual picks as the reference. Error analysis results show that AEnet outperforms AIC-STA/LTA. [ABSTRACT FROM AUTHOR]

The number of client share assessments on Twitter is an important stage for checking and perusing public sentiment. Such checking and review can offer data for choice making in different areas. In these canvases, we move further to translate estimation variants for machine learning algorithms. In trendy, the chaotic variable has unique characters, and firstly chaotic Levy flight is included in the proposed meta-heuristic for successfully delivering new arrangements. Secondly, the psychology version of feeling and confused grouping presented stream acknowledgment choice in the cuckoo search algorithm. Furthermore, we propose an LDA model and Modified Latent Dirichlet Allocation (M-LDA). These M-LDA subjects pick most advisor tweets for changed topics and build up a new setup known as the Emotional Chaotic Cuckoo Search LDA model. The proposed obligations, including discovering point, contrast among two arrangements of documents. [ABSTRACT FROM AUTHOR]

This paper presents the application of an Artificial Intelligence-based method in analyzing the effects of environmental conditions, chloride contamination in concrete, and surface corrosion of rebars on the amplitude of Ground Penetrating Radar (GPR) signals. Six reinforced concrete slabs with different chloride contamination mixtures were fabricated and tested. GPR data were collected under various temperature and ambient humidity combinations. A total of 288 rebar picks were used for training, validation, and testing the proposed Artificial Neural Network (ANN) model. Multiple ANN model configurations with a variation in learning algorithms and the number of nodes in the hidden layer were explored to obtain the optimal model for the nondestructive data. It is shown that the "trainlm" learning algorithm produced the high accuracy prediction of the reflection amplitude of GPR signals. The sensitivity analysis was also conducted with the ANN model to investigate the effects of the input on the output parameters. Results from the sensitivity analysis revealed that the GPR reflection amplitudes were more sensitive to the changes of temperature parameter (TEM) and chloride contamination level (CCL), while they were less sensitive to the variation of ambient relative humidity (ARH) and rust condition on the rebar surface (CSR). [ABSTRACT FROM AUTHOR]

The Laser Powder Bed Fusion (L-PBF) process is being adopted in different industrial fields. However, L-PBF currently lacks process reproducibility and quality. Hence, quality monitoring techniques need to be adopted in order to reduce the process variability and to ensure a high-quality process. Accordingly, this work proposes a quality monitoring approach based on machine learning which links the optical signal of a layer to the density of the final part. The approach consists of selecting relevant statistical features from optical data and validating these features by assessing their ability in predicting the different density classes of different products. Afterwards, the approach is compared to a new deep learning framework that allows predicting a part density from the corresponding raw optical signals. This comparison allows assessing the relevance of the identified statistical features. The proposed monitoring approach is applied on cubical specimens produced with different process parameters, and the results are then discussed and analyzed. [ABSTRACT FROM AUTHOR]

We know that reading involves coordination between textual characteristics and visual attention, but research linking eye movements during reading and comprehension assessed after reading is surprisingly limited, especially for reading long connected texts. We tested two competing possibilities: (a) the weak association hypothesis: Links between eye movements and comprehension are weak and short‐lived, versus (b) the strong association hypothesis: The two are robustly linked, even after a delay. Using a predictive modeling approach, we trained regression models to predict comprehension scores from global eye movement features, using participant‐level cross‐validation to ensure that the models generalize across participants. We used data from three studies in which readers (Ns = 104, 130, 147) answered multiple‐choice comprehension questions ~30 min after reading a 6,500‐word text, or after reading up to eight 1,000‐word texts. The models generated accurate predictions of participants' text comprehension scores (correlations between observed and predicted comprehension: 0.384, 0.362, 0.372, ps <.001), in line with the strong association hypothesis. We found that making more, but shorter fixations, consistently predicted comprehension across all studies. Furthermore, models trained on one study's data could successfully predict comprehension on the others, suggesting generalizability across studies. Collectively, these findings suggest that there is a robust link between eye movements and subsequent comprehension of a long connected text, thereby connecting theories of low‐level eye movements with those of higher order text processing during reading. [ABSTRACT FROM AUTHOR]

Purpose: Accurate prediction of order demand across omni-channel supply chains improves the management's decision-making ability at strategic, tactical and operational levels. The paper aims to develop a predictive methodology for forecasting near-real-time e-commerce order arrivals in distribution centres, allowing third-party logistics service providers to manage the hour-to-hour fast-changing arrival rates of e-commerce orders better. Design/methodology/approach: The paper proposes a novel machine learning predictive methodology through the integration of the time series data characteristics into the development of an adaptive neuro-fuzzy inference system. A four-stage implementation framework is developed for enabling practitioners to apply the proposed model. Findings: A structured model evaluation framework is constructed for cross-validation of model performance. With the aid of an illustrative case study, forecasting evaluation reveals a high level of accuracy of the proposed machine learning approach in forecasting the arrivals of real e-commerce orders in three different retailers at three-hour intervals. Research limitations/implications: Results from the case study suggest that real-time prediction of individual retailer's e-order arrival is crucial in order to maximize the value of e-order arrival prediction for daily operational decision-making. Originality/value: Earlier researchers examined supply chain demand, forecasting problem in a broader scope, particularly in dealing with the bullwhip effect. Prediction of real-time, hourly based order arrivals has been lacking. The paper fills this research gap by presenting a novel data-driven predictive methodology. [ABSTRACT FROM AUTHOR]

Hardware/software co-designs are usually defined at high levels of abstractions at the beginning of the design process in order to provide a variety of options on how to realize a system. This allows for design exploration which relies on knowing the costs of different design configurations (with respect to hardware usage and firmware metrics). To this end, methods for cost estimation are frequently applied in industrial practice. However, currently used methods oversimplify the problem and ignore important features, leading to estimates which are far off from real values. In this article, we address this problem for memory systems. To this end, we borrow and re-adapt solutions based on Machine Learning (ML) which have been found suitable for problems from the domain of Computer Vision (CV). Based on that, an approach is proposed which outperforms existing methods for cost estimation. Experimental evaluations within an industrial context show that, while the accuracy of the state-of-the-art approach is frequently off by more than 20 percent for area estimation and more than 15 percent for firmware estimation, the method proposed in this article comes rather close to the actual values (just 5–7 percent off for both area and firmware). Furthermore, our approach outperforms existing methods for scalability, generalization, and decrease in manual effort. [ABSTRACT FROM AUTHOR]

First break picking is an inevitable process in land seismic data processing, which involves a huge amount of human labor to perform. Even after decades of investigation on the first break picking process, there are still enormous challenges in developing a robust automatic approach. Although many experts proposed techniques to solve the first break picking problems automatically, there are no solid solutions to avoid human labors during the picking process. In the late 20th century, the rise of the artificial intelligence and the advancement of computer hardware have overcome some challenges in first break picking but the level of their success is limited. In this article, we proposed a deep machine learning model to achieve automatic seismic first break picking. Our proposed model can find the underlying factors and determine the first break curve. In addition, the network is capable of updating itself through continuous learning. The system is able to identify labeling anomalies on-site and update the model through active learning. Unfortunately, training the machine learning model on a huge data set that contains unnecessary data points is an inefficient way for both model learning process and human labeling labors. Therefore, training the model with data selected by the experts can highly reduce the training time and the number of data that human has to label. In simulation, we show the advantage of our proposed deep semisupervised neural network, which uses both labeled and unlabeled data sets to achieve higher accuracy compared with the supervised neural networks. [ABSTRACT FROM AUTHOR]

To master ongoing market competitiveness, manufacturing companies try to increase process efficiency through process improvements. Mapping the end-to-end order processing is particularly important, as one needs to consider all order-fulfilling core processes to evaluate process performance. However, today's traditional process mapping methods such as workshops are subjective and time-consuming. Therefore, process improvements are based on gut feeling rather than facts, leading to high failure probabilities. This paper presents a process mining approach that provides data-based description of process performance in order processing and thus objectively and effortlessly maps as-is end-to-end processes. The approach is validated with an industrial case study. [ABSTRACT FROM AUTHOR]

Image captioning is the task of generating textual descriptions of images. In order to obtain a better image representation, attention mechanisms have been widely adopted in image captioning. However, in existing models with detection-based attention, the rectangular attention regions are not fine-grained, as they contain irrelevant regions (e.g., background or overlapped regions) around the object, making the model generate inaccurate captions. To address this issue, we propose panoptic segmentation-based attention that performs attention at a mask-level (i.e., the shape of the main part of an instance). Our approach extracts feature vectors from the corresponding segmentation regions, which is more fine-grained than current attention mechanisms. Moreover, in order to process features of different classes independently, we propose a dual-attention module which is generic and can be applied to other frameworks. Experimental results showed that our model could recognize the overlapped objects and understand the scene better. Our approach achieved competitive performance against state-of-the-art methods. We made our code available. [ABSTRACT FROM AUTHOR]

In order to improve the logistics problem, taking automated logistics system as research platform, a new optimization algorithm is proposed for the route planning of multi-goods picking operation of stacker in stereoscopic warehouse. First, the hardware composition of the automated logistics system is introduced, and then the characteristics of the picking operation of the stacker are deeply analyzed. According to these characteristics, a mathematical model for the time cost of the sorting operation is set up. Various algorithms for solving the problem are analyzed and compared. Aiming at the advantages and disadvantages of ant colony system and parthenogenetic algorithm, the two algorithms are properly improved and fused, and a new improved algorithm—parthenogenetic ant colony algorithm is proposed. The validity is verified by the simulation experiment. The simulation is carried out in the Matlab environment, and the satisfactory optimization results are obtained. The simulation result shows that the algorithm is used to optimize the picking path of the stacker. Therefore, it is concluded that the parthenogenetic algorithm greatly reduces the time of the picking operation, and greatly improves the efficiency. [ABSTRACT FROM AUTHOR]

We present a realtime virtual grasping algorithm to model interactions with virtual objects. Our approach is designed for multi-fingered hands and makes no assumptions about the motion of the user's hand or the virtual objects. Given a model of the virtual hand, we use machine learning and particle swarm optimization to automatically pre-compute stable grasp configurations for that object. The learning pre-computation step is accelerated using GPU parallelization. At runtime, we rely on the pre-computed stable grasp configurations, and dynamics/non-penetration constraints along with motion planning techniques to compute plausible looking grasps. In practice, our realtime algorithm can perform virtual grasping operations in less than 20ms for complex virtual objects, including high genus objects with holes. We have integrated our grasping algorithm with Oculus Rift HMD and Leap Motion controller and evaluated its performance for different tasks corresponding to grabbing virtual objects and placing them at arbitrary locations. Our user evaluation suggests that our virtual grasping algorithm can increase the user's realism and participation in these tasks and offers considerable benefits over prior interaction algorithms, such as pinch grasping and raycast picking. [ABSTRACT FROM AUTHOR]

When a self-adaptive system detects that its adap-tation goals may be compromised, it needs to determine how to adapt to ensure its goals. To that end, the system can analyze the possible options for adaptation, i.e., the adaptation space, and pick the best option that achieves the goals. Such analysis can be resource and time consuming, in particular when rigorous analysis methods are applied. Hence, exhaustively analyzing all options may be infeasible for systems with large adaptation spaces. This problem is further complicated as the adaptation options typically include uncertainty parameters that can only be resolved at runtime. In this paper, we present a machine learning approach to tackle this problem. This approach enhances the traditional MAPE-K feedback loop with a learning module that selects subsets of adaptation options from a large adaptation space to support the analyzer with performing efficient analysis. We instantiate the approach for two concrete learning techniques, classification and regression, and evaluate the approaches for two instances of an Internet of Things application for smart environment monitoring with different sizes of adaptation spaces. The evaluation shows that both learning approaches reduce the adaptation space significantly without noticeable effect on realizing the adaptation goals. [ABSTRACT FROM AUTHOR]

Radio frequency identification (RFID) is an automated identification technology that can be utilized to monitor product movements within a supply chain in real-time. However, one problem that occurs during RFID data capturing is false positives (i.e., tags that are accidentally detected by the reader but not of interest to the business process). This paper investigates using machine learning algorithms to filter false positives. Raw RFID data were collected based on various tagged product movements, and statistical features were extracted from the received signal strength derived from the raw RFID data. Abnormal RFID data or outliers may arise in real cases. Therefore, we utilized outlier detection models to remove outlier data. The experiment results showed that machine learning-based models successfully classified RFID readings with high accuracy, and integrating outlier detection with machine learning models improved classification accuracy. We demonstrated the proposed classification model could be applied to real-time monitoring, ensuring false positives were filtered and hence not stored in the database. The proposed model is expected to improve warehouse management systems by monitoring delivered products to other supply chain partners. [ABSTRACT FROM AUTHOR]