A high-accuracy stacking model for automatic identification of aeolian saltating tracks in high-speed pictures

Spectral-element (SE) method is a kind of higher-order finite-element method based on weighted residual technique; however, the basis functions for SE are polynomial, like Gauss-Lobatto-Legendre (GLL) or Gauss-Lobatto-Chebyshev (GLC) polynomials. Because of its high modeling accuracy and flexibility, it has been successfully used in computational electromagnetism. In this paper, we use the SE method for 3D frequency-domain airborne electromagnetic (AEM) modeling for an anisotropic earth and we take horizontal coplanar and vertical coaxial coil systems as example for the modeling. We first derive the discrete governing equation from Maxwell equations, in which the conductivity tensor is obtained by 3 Euler rotations of a principal conductivity tensor. GLL polynomial is selected as the vector SE basis functions, while GLL integration is applied for calculating matrix elements. A direct solver is used for the solution of the matrix equations system. The modeling accuracy is checked against a semi-analytical solution. Further, we calculate AEM responses for different anisotropic models and demonstrate that SE method canobtain high precision by either increasing SE order or refining meshes, so that it can save computation cost vastly. Numerical results further confirm that the anisotropy of both 3D body and host rock can be identified from the polar plots of ratio of magnetic field components.

PurposeThe purpose of this paper is to propose an improved differential evolution algorithm (DEA) suitable for motor’s model identification.Design/methodology/approachThe mutation operation of the standard DEA is improved, and the adaptive coefficient is designed to adjust the optimization process.FindingsThe application of motor model identification shows that the proposed improved DEA is more robust, with higher modeling accuracy and efficiency, and is more suitable for motor identification modeling applications. Compared with the ultrasonic motor model established by using particle swarm algorithm, the model established in this paper has higher precision.Originality/valueThis paper explores an improved DEA suitable for motor identification modeling. The algorithm can not only obtain the optimal solution but also effectively reduce the iterative generations and time required in the process of optimization identification.

For predicting the voltage and temperature dynamics synchronously and designing a controller, a control-oriented dynamic modeling study of the solid oxide fuel cell (SOFC) derived from physical conservation laws is reported, which considers both the electrochemical and thermal aspects of the SOFC. Here, the least squares support vector regression (LSSVR) is employed to model the nonlinear dynamic characteristics of the SOFC. In addition, a genetic algorithm (GA), through comparing a simulated annealing algorithm (SAA) with a 5-fold cross-validation (5FCV) method, is preferably chosen to optimize the LSSVR’s parameters. The validity of the proposed LSSVR with GA (GA-LSSVR) model is verified by comparing the results with those obtained from the physical model. Simulation studies further indicate that the GA-LSSVR model has a higher modeling accuracy than the LSSVR with SAA (SAA-LSSVR) and the LSSVR with 5FCV (5FCV-LSSVR) models in predicting the voltage and temperature transient behaviors of the SOFC. Furthermore, the convergence speed of the GA-LSSVR model is relatively fast. The availability of this GA-LSSVR identification model can aid in evaluating the dynamic performance of the SOFC under different conditions and can be used for designing valid multivariable control schemes.

Plate culturing and visual inspection are the gold standard methods for bacterial identification. Despite the growing attention on molecular biology techniques, colony identification using agar plates remains manual, interpretative, and heavily reliant on human experience, making it prone to errors. Advanced imaging techniques, like hyperspectral imaging, offer potential alternatives. However, the use of hyperspectral imaging in the VIS-NIR region has been hindered by sensitivity to various components and culture medium changes, leading to inaccurate results. The application of hyperspectral imaging in the ultraviolet (UV) region has not been explored, despite the presence of specific absorption and emission peaks in bacterial components. To address this gap, we developed a predictive model for bacterial colony detection and identification using UV hyperspectral imaging. The model utilizes hyperspectral images acquired in the UV wavelength range of 225-400nm, processed with principal component analysis (PCA) and discriminant analysis (DA). The measurement setup includes a hyperspectral imager, a PC for automated data analysis, and a conveyor belt system to transport agar plates for automated analysis. Four bacterial species (Escherichia coli, Staphylococcus, Pseudomonas, and Shewanella) were cultured on two different media, Luria Bertani and Tryptic Soy, to train and validate the model. The PCA-DA-based model demonstrated high accuracy (90%) in differentiating bacterial species based on the first three principal components, highlighting the potential of UV hyperspectral imaging for bacterial identification. This study shows that UV hyperspectral imaging, coupled with advanced data analysis techniques, offers a robust and automated alternative to traditional methods for bacterial identification. The model's high accuracy emphasizes the untapped potential of UV hyperspectral imaging in microbiological analysis, reducing human error and improving reliability in bacterial species differentiation.

The increasing prevalence of mental health challenges among college students necessitates innovative approaches to early identification and intervention. This study investigates the application of artificial intelligence (AI) techniques for predicting student mental health risks. A hybrid predictive model, Prophet-LSTM, was developed. This model combines the Prophet time series model with Long Short-Term Memory (LSTM) networks to leverage their strengths in forecasting. Prior to model development, association rules between potential mental health risk factors were identified using the Apriori algorithm. These highly associated factors served as inputs for the Prophet-LSTM model. The model's weight coefficients were optimized using the Quantum Particle Swarm Optimization (QPSO) algorithm. The model's performance was evaluated using data from a mental health survey conducted among college students at a Chinese university. The proposed Prophet-LSTM model demonstrated superior performance in predicting student mental health risks compared to other machine learning algorithms. Evaluation metrics, including the detection rate of psychological issues and the detection rate of no psychological issues, confirmed the model's high accuracy. This study demonstrates the potential of AI-powered predictive models for early identification of students at risk of mental health challenges. The findings have significant implications for improving mental health services within higher education institutions. Future research should focus on further refining the model, incorporating real-time data streams, and developing personalized intervention strategies based on the model's predictions.

The conventional fuzzy modelling of short-term load forecasting has a drawback in that the fuzzy rules or the fuzzy membership functions are determined by trial and error. An automatic model identification procedure is proposed to construct the fuzzy model for short-term load forecast. An analysis of variance is used to identify the influential variables of the system load. To set up the fuzzy rules, a cluster estimation method is adopted to determine the number of rules and the membership functions of variables involved in the premises of the rules. A recursive least squares method is then used to determine the coefficients in the concluding parts of the rules. None of these steps involves nonlinear optimisation and all steps have well bounded computation time. This method was tested on the Taiwan Power Company's (Taipower) load data and the performance of the proposed method is compared to those of Box-Jenkins (B-J) transfer function and artificial neural network (ANN) models.

A dual-arm nursing robot can gently lift patients and transfer them between a bed and a wheelchair. With its lightweight design, high load-bearing capacity, and smooth surface, the coupled-drive joint is particularly well suited for these robots. However, the coupled nature of the joint disrupts the direct linear relationship between the input and output torques, posing challenges for dynamic modeling and practical applications. This study investigated the transmission mechanism of this joint and employed the Lagrangian method to construct a dynamic model of its internal dynamics. Building on this foundation, the Newton-Euler method was used to develop a dynamic model for the entire robotic arm. A continuously differentiable friction model was incorporated to reduce the vibrations caused by speed transitions to zero. An experimental method was designed to compensate for gravity, inertia, and modeling errors to identify the parameters of the friction model. This method establishes a mapping relationship between the friction force and motor current. In addition, a Fourier series-based excitation trajectory was developed to facilitate the identification of the dynamic model parameters of the robotic arm. Trajectory tracking experiments were conducted during the experimental validation phase, demonstrating the high accuracy of the dynamic model and the parameter identification method for the robotic arm. This study presents a dynamic modeling and parameter identification method for coupled-drive joint robotic arms, thereby establishing a foundation for motion control in humanoid nursing robots.

A nonlinear autoregressive network with exogenous inputs (NARX) identification model is employed for predicting the Solid oxide fuel cell (SOFC) operating temperature dynamics fast and accurately in a Solid oxide fuel cell–gas turbine (SOFC-GT) hybrid system. At the same time, the least squares support vector regression (LSSVR) method with radial basis kernel function (RBF) which uses particle swarm optimization (PSO) to optimize the LSSVR’s parameters is applied to establish the NARX model. The major factors which affect the cathode and anode outlet temperature of the SOFC-GT hybrid system are the inlet flow rate of cathode and anode. Therefore, the inlet flow rates of cathode and anode are taken as inputs of the NARX model, cathode and anode outlet temperature as outputs. With the training data sampled from the mechanism model which is derived from conservation laws, a SOFC temperature the NARX model based on the LSSVR is established. Investigations are conducted to analyze the effects of training data size and fitness function of PSO on the accuracy of the NARX model. And by comparing the temperature behaviors with the results collected form the mechanism model, the accuracy of the NARX model based on the LSSVR is verified with enough accuracy in predicting the dynamic performance of the SOFC temperature. Furthermore, in the aspect of simulation speed, the NARX model is much faster than the mechanism model because the NARX model avoids the internal complex computation process. For large size training data, the training time of the NARX model is only about 1.2s. For running all 20,000s of simulation, the predicting time of the NARX model is only about 0.2s, while the mechanism model is about 36s. In consideration of the high speed and accuracy of the NARX model, it can be applied to design valid multivariable model predictive control (MPC) schemes with high reputation.

The characterization and analysis of rock types based on acoustic emission (AE) signals have long been focal points in earth science research. However, traditional analysis methods struggle to handle the influx of big data. While signal processing methods combined with deep learning have found widespread use in various process analyses and state identification, effective feature extraction using progressive fusion technology still faces challenges in the field of intelligent rock type identification. To address this issue, our study proposes a novel framework for rock type identification based on AE and introduces a new signal identification model called 3CTNet. This model integrates convolutional neural networks (CNNs) and Transformer encoder, intelligently identifying AE of different rock fractures by establishing dependencies between adjacent positions within the data and gradually extracting advanced features. Furthermore, we experimentally compare five oversampling methods, ultimately selecting the adaptive synthetic sampling method (ADASYN) to balance the dataset and enhance the model's robustness and generalization ability. Comparison of the internal structure of our model with a series of time series processing models demonstrates the effectiveness of the proposed model structure. Experimental results showcase the high identification accuracy of the intelligent rock type identification model based on 3CTNet, with an overall identification accuracy reaching 98.780%. Our proposed method lays a solid foundation for the efficient and accurate identification of formation rock types in geological exploration and oil and gas development endeavors.

Identification and generation of Quality Attribute Scenarios (QASs) from Quality Attribute Requirements (QARs) is a critical software engineering technique for defining system specifications and is helpful in facilitating development of Software Architecture (SA) that meets the expected quality. However, identifying QAS types and extracting their components traditionally is a complex task that consumes time and energy. It also requires high budget and is an error-prone task, especially for inexperienced users. This study aims to develop an automatic QASs identification and generation model that extracts QASs from QARs. We used Natural Language Processing (NLP) to preprocess texts and Machine Learning (ML) approaches to identify QAS types, and we built a Custom Named Entity Recognition (CNER) model to generate QAS components. To evaluate the proposed identification model, we used five algorithms. Both SVM and Scholastic Gradient Descent (SGD) classifier algorithms scored 97.7 % accuracy, while LR, KNN, and NB scored 96%, 91.6 %, and 88.8%, respectively. The CNER model achieved 92.3% recall, 93.3% precision, and 92.8% F1-measure score. The results show that automatic identification of QASs from QARs has a potential to replace time taking and error-prone manual work.

Safety risk identification throughout deep excavation construction is an information-intensive task, involving construction information scattered in project planning documentation and dynamic information obtained from different field sensors. However, inefficient information integration and exchange have been an important obstacle to the development of automatic safety risk identification in actual applications. This research aims to achieve the requirements for information integration and exchange by developing a semantic industry foundation classes (IFC) data model based on a central database of Building Information Modeling (BIM) in dynamic deep excavation process. Construction information required for risk identification in dynamic deep excavation is analyzed. The relationships among construction information are identified based on the semantic IFC data model, involved relationships (i.e., logical relationships and constraints among risk events, risk factors, construction parameters, and construction phases), and BIM elements. Furthermore, an automatic safety risk identification approach is presented based on the semantic data model, and it is tested through a construction risk identification prototype established under the BIM environment. Results illustrate the effectiveness of the BIM-based central database in accelerating automatic safety risk identification by linking BIM elements and required construction information corresponding to the dynamic construction process.

Parameter identification of reduced-order electrochemical model simplified by spectral methods and state estimation based on square-root cubature Kalman filter

Functionally Pooled models for the global identification of stochastic systems under different pseudo-static operating conditions

Annotations of character IDs in news images are critical as ground truth for news retrieval and recommendation system. Universality and accuracy optimization of deep neural network models constitutes the key technology to improve the precision and computing efficiency of automatic news character identification, which is attracting increased attention globally. This paper explores the optimized deep neural network model for automatic focus personage identification in multi-lingual news. First, the face model of the focus personage is trained by using the corresponding face images from German news as positive samples. Next, the scheme of Recurrent Convolutional Neural Network (RCNN) + Bi-directional Long-Short Term Memory (Bi-LSTM) + Conditional Random Field (CRF) is utilized to label the focus name, and the RCNN-RCNN encoder–decoder is applied to translate names of people into multiple languages. Third, face features are described by combining the advantages of Local Gabor Binary Pattern Histogram Sequence (LGBPHS) and RCNN, and iterative quantization (ITQ) is used to binarize codes. Finally, a name semantic network is built for different domains. Experiments are performed on a dataset which comprises approximately 100,000 news images. The experimental results demonstrate that the proposed method achieves a significant improvement over other algorithms.

Monitoring single-channel EEG is a promising home-based approach for insomnia identification. Currently, many automatic sleep stage scoring approaches based on single-channel EEG have been developed, whereas few studies research on automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations. In this paper, we propose a one-dimensional convolutional neural network (1D-CNN) model for automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations, and further investigate the identification performance based on different sleep stages EEG epochs. Single-channel EEG on 9 insomnia patients and 9 healthy subjects was used in this study. We constructed 4 subdatasets from EEG epochs based on the sleep stage annotations: All sleep stage dataset (ALL-DS), REM sleep stage dataset (REM-DS), light sleep stage dataset (LSS-DS), and SWS sleep stage dataset (SWS-DS). Subsequently, 4 subdatasets were fed into our 1D-CNN. We conducted experiments under intra-patient and inter-patient paradigms, respectively. Our experiments demonstrated that our 1D-CNN leveraging 3 subdatasets composed of REM, LSS and SWS epochs, respectively, achieved higher average accuracies in comparison with baseline methods under both intra-patient and inter-patient paradigms. The experimental results also indicated that amongst all the sleep stages, 1D-CNN leveraging REM and SWS epochs exhibited the best insomnia identification average accuracies in intra-patient paradigm, which are 98.98% and 99.16% respectively, whereas no statistically significant difference was found in inter-patient paradigm. For automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations, 1D-CNN model introduced in this paper could achieve superior performance than traditional methods.