Search

Introduction: With the rapid development of artificial intelligence and machine learning technology, image processing technology based on artificial intelligence and machine learning has been applied in various fields, which effectively solves the multi-classification problem of similar targets in traditional image processing technology. Methods: This paper summarizes the various algorithms of artificial intelligence and machine learning in image processing, the development process of neural network model, the principle of model and the advantages and disadvantages of different algorithms, and introduces the specific application of image processing technology based on these algorithms in different scientific research fields. Results And Discussion: The application of artificial intelligence and machine learning in image processing is summarized and prospected, in order to provide some reference for researchers who used artificial intelligence and machine learning for image processing in different fields. [ABSTRACT FROM AUTHOR]

Background: The diagnostic accuracy of colon capsule endoscopy (CCE) depends on a well-cleansed bowel. Evaluating the cleansing quality can be difficult with a substantial interobserver variation. Objectives: Our primary aim was to establish a standard of agreement for bowel cleansing in CCE based on evaluations by expert readers. Then, we aimed to investigate the interobserver agreement on bowel cleansing. Design: We conducted an interobserver agreement study on bowel cleansing quality. Methods: Readers with different experience levels in CCE and colonoscopy evaluated bowel cleansing quality on the Leighton–Rex scale and Colon Capsule CLEansing Assessment and Report (CC-CLEAR), respectively. All evaluations were reported on an image level. A total of 24 readers rated 500 images on each scale. Results: An expert opinion-based agreement standard could be set for poor and excellent cleansing but not for the spectrum in between, as the experts agreed on only a limited number of images representing fair and good cleansing. The overall interobserver agreement on the Leighton–Rex full scale was good (intraclass correlation coefficient (ICC) 0.84, 95% CI (0.82–0.85)) and remained good when stratified by experience level. On the full CC-CLEAR scale, the overall agreement was moderate (ICC 0.62, 95% CI (0.59–0.65)) and remained so when stratified by experience level. Conclusion: The interobserver agreement was good for the Leighton–Rex scale and moderate for CC-CLEAR, irrespective of the reader's experience level. It was not possible to establish an expert-opinion standard of agreement for cleansing quality in CCE images. Dedicated training in using the scales may improve agreement and enable future algorithm calibration for artificial intelligence supported cleansing evaluation. Trial registration: All included images were derived from the CAREforCOLON 2015 trial (Registered with The Regional Health Research Ethics Committee (Registration number: S-20190100), the Danish data protection agency (Ref. 19/29858), and ClinicalTrials.gov (registration number: NCT04049357)). [ABSTRACT FROM AUTHOR]

BACKGROUND: The process of acquiring visual data from microelectromechanical sensors currently requires significant time and effort on the part of the clinician. The use of artificial intelligence algorithms to approximate data could potentially reduce the time required and increase the amount of work performed. AIM: The aim of this study is to approximate the data generated by sensors located in the shoe insole of basketball athletes and to compare the change in movement parameters of athletes when using CAD/CAM insoles. MATERIALS AND METHODS: Prior to the commencement of the study, permission was obtained from the local ethical committee of Sechenov University (protocol No. 19–23). The main cohort consisted of 39 athletes, comprising 21 men (53%) and 18 women (47%). The mean age of the athletes was 22.4 ± 7.54 years. The athletes were divided into three equal comparison groups according to the type of insoles they were wearing. Throughout the study period, all athletes remained healthy and free from injuries. The assessment of movement in space was conducted using a three-test system. This involved the use of microelectromechanical system sensors with an artificial intelligence algorithm, which facilitated the construction of visually clear and well-interpreted median lines (data approximation). RESULTS: For objective assessment of jumping characteristics, angular changes, velocity movements in space, and a comparison of all parameters on days 0 and 21, we developed and used our own software system, which was based on mathematical algorithmization and transformation formulas on specific axes. All data were entered into a neural network to construct averaged values of the parameters of movement in space. This approach allows the doctor to evaluate the changes of each peak movement on three different axes. Furthermore, it is possible to summarize the athlete's movement parameters with the aid of artificial intelligence, thereby enabling the detection of changes in different axes on days 0 and 21. Insole model C-1 exhibited the following improvements: X-axis movement speed (+7.7%), Y-axis jump height (+17.3%), endurance (+3.1%), and a 1.43-fold enhancement in shock absorption. Insole model C-2 exhibited an 8.4% increase in X-axis travel speed, a 20.8% enhancement in Y-axis jump height, a 6.6% improvement in endurance, and a 1.48-fold enhancement in shock absorption. Insole model C-3 demonstrated an 13.5% surge in X-axis travel speed, a 22.4% surge in Y-axis jump height, a 9.5% surge in endurance, and a 1.53-fold enhancement in shock absorption. CONCLUSIONS: The approximation of the data (median lines using an artificial intelligence algorithm) allows for the straightforward interpretation and comparison of various parameters, as well as the drawing of conclusions regarding the efficacy of individual sports CAD/CAM insoles. Additionally, it enables the assessment of changes in endurance, speed of movement during prolonged and intensive movement, and the reduction of the risk of impact loads on the musculoskeletal system of the athlete.

Introduction: Endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) for lung cancer staging is operator dependent, resulting in high rates of non-diagnostic lymph node (LN) samples. We hypothesized that an artificial intelligence (AI) algorithm can consistently and reliably predict nodal metastases from the ultrasound images of LNs when compared to pathology. Methods: In this analysis of prospectively recorded B-mode images of mediastinal LNs during EBUS-TBNA, we used transfer learning to build an end-to-end ensemble of three deep neural networks (ResNet152V2, InceptionV3, and DenseNet201). Model hyperparameters were tuned, and the optimal version(s) of each model was trained using 80% of the images. A learned ensemble (multi-layer perceptron) of the optimal versions was applied to the remaining 20% of the images (Test Set). All predictions were compared to the final pathology from nodal biopsies and/or surgical specimen. Results: A total of 2,569 LN images from 773 patients were used. The Training Set included 2,048 LNs, of which 70.02% were benign and 29.98% were malignant on pathology. The Testing Set included 521 LNs, of which 70.06% were benign and 29.94% were malignant on pathology. The final ensemble model had an overall accuracy of 80.63% (95% confidence interval [CI]: 76.93–83.97%), 43.23% sensitivity (95% CI: 35.30–51.41%), 96.91% specificity (95% CI: 94.54–98.45%), 85.90% positive predictive value (95% CI: 76.81–91.80%), 79.68% negative predictive value (95% CI: 77.34–81.83%), and AUC of 0.701 (95% CI: 0.646–0.755) for malignancy. Conclusion: There now exists an AI algorithm which can identify nodal metastases based only on ultrasound images with good overall accuracy, specificity, and positive predictive value. Further optimization with larger sample sizes would be beneficial prior to clinical application. [ABSTRACT FROM AUTHOR]

Gait instability is critical in medicine and healthcare, as it has associations with balance disorder and physical impairment. With the development of sensor technology, despite the fact that numerous wearable gait detection and recognition systems have been designed to monitor users' gait patterns, they commonly spend a lot of time and effort to extract gait metrics from signal data. This study aims to design an artificial intelligence-empowered and economic-friendly gait monitoring system. A pair of intelligent shoes with a single inertial sensor and a smartphone application were developed as a gait monitoring system to detect users' gait cycle, stand phase time, swing phase time, stride length, and foot clearance. We recruited 30 participants (24.09 ± 1.89 years) to collect gait data and used the Vicon motion capture system to verify the accuracy of the gait metrics. The results show that the gait monitoring system performs better on the assessment of the gait metrics. The accuracy of stride length and foot clearance is 96.17% and 92.07%, respectively. The artificial intelligence-empowered gait monitoring system holds promising potential for improving gait analysis and monitoring in the medical and healthcare fields. [ABSTRACT FROM AUTHOR]

Objectives: We aimed to construct an artificial intelligence‐enabled electrocardiogram (ECG) algorithm that can accurately predict the presence of left atrial low‐voltage areas (LVAs) in patients with persistent atrial fibrillation. Methods: The study included 587 patients with persistent atrial fibrillation who underwent catheter ablation procedures between March 2012 and December 2023 and 942 scanned images of 12‐lead ECGs obtained before the ablation procedures were performed. Artificial intelligence‐based algorithms were used to construct models for predicting the presence of LVAs. The DR‐FLASH and APPLE clinical scores for LVA prediction were calculated. We used a receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis to evaluate model performance. Results: The data obtained from the participants were split into training (n = 469), validation (n = 58), and test sets (n = 60). LVAs were detected in 53.7% of all participants. Using ECG alone, the deep learning algorithm achieved an area under the ROC curve (AUROC) of 0.752, outperforming both the DR‐FLASH score (AUROC = 0.610) and the APPLE score (AUROC = 0.510). The random forest classification model, which integrated a probabilistic deep learning model and clinical features, showed a maximum AUROC of 0.759. Moreover, the ECG‐based deep learning algorithm for predicting extensive LVAs achieved an AUROC of 0.775, with a sensitivity of 0.816 and a specificity of 0.896. The random forest classification model for predicting extensive LVAs achieved an AUROC of 0.897, with a sensitivity of 0.862, and a specificity of 0.935. Conclusion: The deep learning model based exclusively on ECG data and the machine learning model that combined a probabilistic deep learning model and clinical features both predicted the presence of LVAs with a higher degree of accuracy than the DR‐FLASH and the APPLE risk scores. [ABSTRACT FROM AUTHOR]

The increasing apprehension for health, safety and quality of life in modern society has resulted in the widespread use of biosensors. Biosensors are characterised by their high sensitivity, real‐time monitoring, and easy integration, making them indispensable for environmental monitoring on‐site, as well as invasive and non‐invasive health monitoring. Signal processing and analysis are crucial to biosensor applications, with an important role being played by chemometrics in this regard. This review presents a review of recent research findings in the fields of environmental and health monitoring. In addition, it investigates the role that chemometrics plays in the processing and analysis of biosensor data. The research comprises conventional statistical techniques, including principal component analysis and wavelet transform, as well as modern techniques of artificial intelligence, such as machine learning with neural networks. Through the examination of various algorithm strengths and weaknesses, significant recommendations are offered for biosensor applications. Furthermore, the assessment delivers focused proposals for surmounting signal processing difficulties in biosensors. Additionally, the review contains a concise analysis and reflection on the issue of multiple detection and analysis. The review intends to give essential guidance to future researchers in selecting efficient and sensible methods of data processing for their studies. [ABSTRACT FROM AUTHOR]

This study follows a novel path toward alarming the dangerous conditions of the buildings by means of piezoelectricity. piezoelectric materials have the ability to translate electrical voltage and displacement to each other interchangeably. This feature is employed in this research to define a critical threshold for the displacements. The case study of this research is a graphene-platelets reinforced functionally-graded piezoelectric (GPLR-FGP) rectangular wall with one free edged at its top. The voltage would be gradually increased until the natural frequency approaches to zero. This circumstance puts the wall in the direct danger of failing its stability. Accordingly, displacements of the wall at this condition can be considered as the critical deflections of the system. The wall's governing equations are established in the background of higher-order shear deformation theory (HOSDT). Differential quadrature approach (DQA) is employed to obtain the natural frequency of the wall. Deep-learning is utilized to accelerate the computation process by means of training a deep network of neurons through the instances determined by the explained numerical approach. Efficiency of the innovative implemented solution in this research is verified through a comparative analysis with the results of the published articles. This research can be considered as the main stone of developing innovative solutions for alarming safety issues in the smart cities of near future. [ABSTRACT FROM AUTHOR]

This research aims to apply Artificial Intelligence (AI) methods, specifically Artificial Immune Systems (AIS), to design an optimal control strategy for a multivariable control plant. Two specific industrial control approaches are investigated: I-PD (Integral-Proportional Derivative) and PI-D (Proportional-Integral Derivative) control. The motivation for using these variations of PID controllers is that they are functionally implemented in modern industrial controllers, where they provide precise process control. The research results in a novel solution to the control synthesis problem for the industrial system. In particular, the research deals with the synthesis of I-P control for a two-loop system in the technological process of a distillation column. This synthesis is carried out using the AIS algorithm, which is the first application of this technique in this specific context. Methodological approaches are proposed to improve the performance of industrial multivariable control systems by effectively using optimization algorithms and establishing modified quality criteria. The numerical performance index ISE justifies the effectiveness of the AIS-based controllers in comparison with conventional PID controllers (ISE1 = 1.865, ISE2 = 1.56). The problem of synthesis of the multi-input multi-output (MIMO) control system is solved, considering the interconnections due to the decoupling procedure. [ABSTRACT FROM AUTHOR]

The aim of this research is to explore the application value of Deep residual network model (DRN) for deep learning-based multi-sequence magnetic resonance imaging (MRI) in the staging diagnosis of cervical cancer (CC). This research included 90 patients diagnosed with CC between August 2019 and May 2021 at the hospital. After undergoing MRI examination, the clinical staging and surgical pathological staging of patients were conducted. The research then evaluated the results of clinical staging and MRI staging to assess their diagnostic accuracy and correlation. In the staging diagnosis of CC, the feature enhancement layer was added to the DRN model, and the MRI imaging features of CC were used to enhance the image information. The precision, specificity, and sensitivity of the constructed model were analyzed, and then the accuracy of clinical diagnosis staging and MRI staging were compared. As the model constructed DRN in this research was compared with convolutional neural network (CNN) and the classic deep neural network visual geometry group (VGG), the precision was 67.7, 84.9, and 93.6%, respectively. The sensitivity was 70.4, 82.5, and 91.2%, while the specificity was 68.5, 83.8, and 92.2%, respectively. The precision, sensitivity, and specificity of the model were remarkably higher than those of CNN and VGG models (P < 0.05). As the clinical staging and MRI staging of CC were compared, the diagnostic accuracy of MRI was 100%, while that of clinical diagnosis was 83.7%, showing a significant difference between them (P < 0.05). Multi-sequence MRI under intelligent algorithm had a high diagnostic rate for CC staging, deserving a good clinical application value.

Interior design is a complex system that includes many elements, such as user needs, spatial structure, material selection, color matching, lighting layout, etc. The relationships between them are complex and intricate. How to design space according to user needs is one of the most challenging issues in interior design. A distributed 3D interior design system based on artificial intelligence algorithms was adopted to address this issue. The system divided indoor spatial information into several subsets. It assigned subsets to various professional designers based on user needs, and generated multiple design schemes through artificial intelligence algorithms, which were then screened, modified, and optimized by each professional designer. In this way, designers from different professional backgrounds can personalized design the space according to their own understanding, thereby avoiding issues such as information fragmentation and low efficiency in traditional interior design. The results showed that the distributed 3D interior design system based on artificial intelligence algorithms can improve the overall performance from an average of 82.68% to 94.94%, effectively avoiding the problem of information fragmentation. [ABSTRACT FROM AUTHOR]

Intelligent manufacturing is the main direction of Industry 4.0, pointing towards the future development of manufacturing. The core component of intelligent manufacturing is the computer numerical control (CNC) system. Predicting and compensating for machining trajectory errors by controlling the CNC system's accuracy is of great significance in enhancing the efficiency, quality, and flexibility of intelligent manufacturing. Traditional machining trajectory error prediction and compensation methods make it challenging to consider the uncertainties that occur during the machining process, and they cannot meet the requirements of intelligent manufacturing with respect to the complexity and accuracy of process parameter optimization. In this paper, we propose a hybrid-model-based machining trajectory error prediction and compensation method to address these issues. Firstly, a digital twin framework for the CNC system, based on a hybrid model, was constructed. The machining trajectory error prediction and compensation mechanisms were then analyzed, and an artificial intelligence (AI) algorithm was used to predict the machining trajectory error. This error was then compensated for via the adaptive compensation method. Finally, the feasibility and effectiveness of the method were verified through specific experiments, and a realization case for this digital-twin-driven machining trajectory error prediction and compensation method was provided. [ABSTRACT FROM AUTHOR]

Medical imaging serves as a crucial tool in current cancer diagnosis. However, the quality of medical images is often compromised to minimize the potential risks associated with patient image acquisition. Computer-aided diagnosis systems have made significant advancements in recent years. These systems utilize computer algorithms to identify abnormal features in medical images, assisting radiologists in improving diagnostic accuracy and achieving consistency in image and disease interpretation. Importantly, the quality of medical images, as the target data, determines the achievable level of performance by artificial intelligence algorithms. However, the pixel value range of medical images differs from that of the digital images typically processed via artificial intelligence algorithms, and blindly incorporating such data for training can result in suboptimal algorithm performance. In this study, we propose a medical image-enhancement scheme that integrates generic digital image processing and medical image processing modules. This scheme aims to enhance medical image data by endowing them with high-contrast and smooth characteristics. We conducted experimental testing to demonstrate the effectiveness of this scheme in improving the performance of a medical image segmentation algorithm. [ABSTRACT FROM AUTHOR]

The recognition technology of coal and gangue is one of the key technologies of intelligent mine construction. Aiming at the problems of the low accuracy of coal and gangue recognition models and the difficult recognition of small-target coal and gangue caused by low-illumination and high-dust environments in the coal mine working face, a coal and gangue recognition model based on the improved YOLOv7-tiny target detection algorithm is proposed. This paper proposes three model improvement methods. The coordinate attention mechanism is introduced to improve the feature expression ability of the model. The contextual transformer module is added after the spatial pyramid pooling structure to improve the feature extraction ability of the model. Based on the idea of the weighted bidirectional feature pyramid, the four branch modules in the high-efficiency layer aggregation network are weighted and cascaded to improve the recognition ability of the model for useful features. The experimental results show that the average precision mean of the improved YOLOv7-tiny model is 97.54%, and the FPS is 24.73 f·s−1. Compared with the Faster-RCNN, YOLOv3, YOLOv4, YOLOv4-VGG, YOLOv5s, YOLOv7, and YOLOv7-tiny models, the improved YOLOv7-tiny model has the highest recognition rate and the fastest recognition speed. Finally, the improved YOLOv7-tiny model is verified by field tests in coal mines, which provides an effective technical means for the accurate identification of coal and gangue. [ABSTRACT FROM AUTHOR]

Gasification technology is an effective way to achieve high value-added utilization of solid waste. In this work, a typical fluidized bed reactor was used to investigate the gasification of pinewood particles. The influence of temperature, equivalence ratio (ER), and steam/biomass ratio on product yield was investigated. Experimental results show that higher temperature benefited the yield of syngas while inhibited the yield of biochar. Increasing ER benefited the gasification reactions but too much air would cause over oxidation and lower the concentration of H2 and CO. Artificial neural network (ANN) model and particle swarm optimization (PSO) coupled with ANN model were built to predict the product yield during waste gasification. The optimized transfer function for hidden layer is logsig, with optimized neuron number of 12. Network weight analysis shows that hydrogen content, gasification temperature, carbon content, and ER are the largest impact variables for H2 concentration, CO concentration, biochar yield, and syngas yield, respectively. PSO-ANN model results show that the PSO algorithm could be used to optimize the weight of ANN model and significantly improve the prediction accuracy. The largest deviation for CO concentration reduced from 13.93 to 8.39%. Results proved that ANN model can be used as an effective tool to predict the product distribution in solid waste gasification. [ABSTRACT FROM AUTHOR]

Gait instability is critical in medicine and healthcare, as it has associations with balance disorder and physical impairment. With the development of sensor technology, despite the fact that numerous wearable gait detection and recognition systems have been designed to monitor users’ gait patterns, they commonly spend a lot of time and effort to extract gait metrics from signal data. This study aims to design an artificial intelligence-empowered and economic-friendly gait monitoring system. A pair of intelligent shoes with a single inertial sensor and a smartphone application were developed as a gait monitoring system to detect users’ gait cycle, stand phase time, swing phase time, stride length, and foot clearance. We recruited 30 participants (24.09 ± 1.89 years) to collect gait data and used the Vicon motion capture system to verify the accuracy of the gait metrics. The results show that the gait monitoring system performs better on the assessment of the gait metrics. The accuracy of stride length and foot clearance is 96.17% and 92.07%, respectively. The artificial intelligence-empowered gait monitoring system holds promising potential for improving gait analysis and monitoring in the medical and healthcare fields.

This research aims to apply Artificial Intelligence (AI) methods, specifically Artificial Immune Systems (AIS), to design an optimal control strategy for a multivariable control plant. Two specific industrial control approaches are investigated: I-PD (Integral-Proportional Derivative) and PI-D (Proportional-Integral Derivative) control. The motivation for using these variations of PID controllers is that they are functionally implemented in modern industrial controllers, where they provide precise process control. The research results in a novel solution to the control synthesis problem for the industrial system. In particular, the research deals with the synthesis of I-P control for a two-loop system in the technological process of a distillation column. This synthesis is carried out using the AIS algorithm, which is the first application of this technique in this specific context. Methodological approaches are proposed to improve the performance of industrial multivariable control systems by effectively using optimization algorithms and establishing modified quality criteria. The numerical performance index ISE justifies the effectiveness of the AIS-based controllers in comparison with conventional PID controllers (ISE1 = 1.865, ISE2 = 1.56). The problem of synthesis of the multi-input multi-output (MIMO) control system is solved, considering the interconnections due to the decoupling procedure.

The fault diagnosis problem of analog circuits has been paid more and more attention, and the realization of circuit fault feature extraction and pattern classification are two of the key problems. This paper first combines wavelet packet and energy entropy to design a fault feature extraction method based on wavelet packet entropy to solve the problem of analog circuit fault feature extraction. Secondly, the principle of SVM and particle swarm optimization algorithm are combined to design the fault diagnosis process of analog circuits based on an artificial intelligence algorithm. Finally, take the sallen-key circuit as an example to analyze the effectiveness of the wavelet packet entropy algorithm for fault feature extraction and analyze the effectiveness of this paper’s method based on the analog circuit of Wen’s bridge oscillation circuit. The results show that after wavelet packet entropy extraction of the feature vector values is less than 0.001, and the accuracy of the extraction is more than 0.98, the best parameters of the optimization is (182.4, 0.05), the false alarm rate of the fault diagnostic method is 0, the misdiagnosis rate is 0.08, the omission rate is 0, and the correctness rate of the diagnosis of the fault is 0.92. Based on this research is able to carry out the fault diagnosis of the analog circuit.

To better improve student performance and make students more receptive to knowledge, a study of artificial intelligence algorithms for the development and evaluation of college teachers’ teaching skills is proposed. Connections are established with multiple neurons in the periphery through dendrites and axons, and weighted integration of neuronal inputs to the next neuron, given an intelligent learning target. The sensitivity is back-propagated in the adjustment of model parameters, and the centroids are selected to calculate the Euclidean distance to obtain an accurate prediction model, and the weight parameters and bias vectors of the model are adjusted. Using a two-by-two comparison to determine the hierarchical factors, the weights of the relative importance of all factors at each level were calculated and ranked, and the multi-level index system was formed according to the constraint relationship between factors. According to the hierarchical structure of the teaching ability of college teacher educators and the opinions of some experts, the weights of each element in each matrix were determined to reasonably evaluate the effective teaching ability of college teachers in the classroom. The analysis results show that the artificial neural network model has a relative error value of about 1.5% and high numerical accuracy in evaluating teachers’ classroom teaching ability by hierarchical analysis.

To make the computer useful in the field of artificial intelligence in the context of big data. In this paper, based on the analysis and comparison of the big data algorithm model and artificial intelligence algorithm in computers, we propose an algorithm based on a decision tree and logistic regression model in big data to query literature papers in the field of artificial intelligence as an example and compare and analyze the accuracy, accuracy, completeness, and F1 value of the obtained data through two categories of experiments. The experimental results show that the decision tree and logistic regression algorithm model based on big data can make the data finding accuracy of 89%, accuracy of 92%, and completeness of 87%, and optimize the speed and quality of the computer algorithm in the process of processing big data. This shows that the computer in the context of big data can provide access to data through algorithmic models in the field of artificial intelligence, which can improve the accuracy and authenticity of data sources and provide data support for in-depth research in the field of artificial intelligence.

Due to its advantages of high acceleration, reusability, environmental protection, safety, energy conservation, and efficiency, electromagnetic energy has been considered as an inevitable choice for future space launch technology. This paper proposes a novel three-level orbital launch approach based on a combination of a traditional two-level orbital launch method and an electromagnetic boost (EMB), in which the traditional two-level orbital launch consists of a turbine-based combined cycle (TBCC) and a reusable rocket (RR). Firstly, a mathematical model of a multi-stage coil electromagnetic boost system is established to develop the proposed three-level EMB-TBCC-RR orbital launch approach, achieving a horizontal take-off–horizontal landing (HTHL) reusable launch. In order to optimize the fuel quality of the energy system, an artificial intelligence algorithm parameters-sensitivity-based adaptive quantum-inspired glowworm swarm optimization (AQGSO)is proposed to improve the performance of the electromagnetic boosting system. Simulation results show that the proposed AQGSO improves the global optimization precision and convergence speed. By using the proposed EMB-TBCC-RR orbital launch system and the optimization approach, the required fuel weight was reduced by about 13 tons for the same launch mission, and the energy efficiency and reusability of the spacecraft was greatly improved. The spacecraft can be launched with more cargo capacity and increased payload. The proposed novel three-level orbital launch approach can help engineers to design and optimize the orbital launch system in the field of electromagnetic energy conversion and management. [ABSTRACT FROM AUTHOR]

The one-dimensional cutting-stock problem (1D-CSP) consists of obtaining a set of items of different lengths from stocks of one or different lengths, where the minimization of waste is one of the main objectives to be achieved. This problem arises in several industries like wood, glass, and paper, among others similar. Different approaches have been designed to deal with this problem ranging from exact algorithms to hybrid methods of heuristics or metaheuristics. The African Buffalo Optimization (ABO) algorithm is used in this work to address the 1D-CSP. This algorithm has been recently introduced to solve combinatorial problems such as travel salesman and bin packing problems. A procedure was designed to improve the search by taking advantage of the location of the buffaloes just before it is needed to restart the herd, with the aim of not to losing the advance reached in the search. Different instances from the literature were used to test the algorithm. The results show that the developed method is competitive in waste minimization against other heuristics, metaheuristics, and hybrid approaches. [ABSTRACT FROM AUTHOR]

Practical analysis and forecasting of PM2.5 concentrations is complex and challenging owing to the volatility and non‐stationarity of PM2.5 series. Most previous studies mainly focused on deterministic predictions, whereas the uncertainty in the prediction is not considered. In this study, a novel uncertainty analysis–forecasting system comprising distribution function analysis, intelligent deterministic prediction, and interval prediction is designed. Based on the characteristics of PM2.5 series, 16 hybrid models composed of various distribution functions and swarm optimization algorithms are selected to determine the exact PM2.5 distribution. Subsequently, a hybrid deterministic forecasting model based on a novel decomposition–ensemble framework is established for PM2.5 prediction. Regarding uncertainty analysis, interval prediction is established to provide uncertain information required for decision–making based on the optimal distribution functions and deterministic prediction results. PM2.5 concentration series obtained from three cities in China are used to conduct an empirical study. The empirical results show that the proposed system can achieve better prediction results than other comparable models as well as provide meaningful and practical quantification of future PM trends. Hence, the system can provide more constructive suggestions for government administrators and the public. [ABSTRACT FROM AUTHOR]

The Jigongshan Mountain Tunnel in Shenzhen China is 4.6 km in length and designed to cross underneath the Xiaping Municipal Solid Waste Landfill. The estimation of the in situ stress field along the tunnel, particularly under the Xiaping landfill, has posed significant challenges. In this study, an integrated strategy comprising multisource information analysis and intelligent back analysis was developed to predict the in situ stress of the study region. First, the regime of in situ stress was estimated based on multisource information, including geological history, geological structure, topography, rock type, joint, and measured stress. Then, multiple linear regression and particle swarm optimization (PSO) method coupled with extreme learning machine (ELM) method were introduced into the intelligent back analysis to identify the orientation and magnitude of the in situ stress along the tunnel. By simultaneously considering the effects of gravity, tectonic stress, rock and fault parameters, and landfill load on the in situ stress, the sum of squares for error in simulation of in situ stress significantly decreases by 23%. Finally, the accuracy of the predicted in situ stress field and the reliability of the proposed integrated method were substantiated through a comprehensive comparison between the simulated and measured rock displacement acquired during the tunnel excavation process. The characteristics of the in situ stress along the tunnel and under the landfill were successfully identified. The landfill load predominantly influences the vertical stress under the landfill, while it does not alter the three-dimensional state of stress. This study serves as a valuable reference for identifying the in situ stress in regions with varying upper loads and limitations on conducting field measurements. [ABSTRACT FROM AUTHOR]

Against the background of the current complex international geopolitical situation and more intense trade frictions, the volatility of financial assets has important research significance as a basis for risk analysis and option pricing. First, considering the characteristics of financial assets—such as "long dependence"—the pricing model can become complicated, making it difficult to calculate the implied volatility directly. Establishing the loss function between the trading data and modeled value, the implied volatility at different moments solved using the global optimal double annealing algorithm was found to differ from the generalized autoregressive conditional heteroskedasticity (GARCH) volatility and historical volatility. Second, the implied volatility considering people's future expectations of financial assets was predicted using the previously known implied volatility via deep learning methods. The empirical results showed that the implied volatilities predicted using the long short-term memory (LSTM) and one-dimensional convolutional neural network (1D-CNN) methods performed well for option pricing. Moreover, the fractal option-pricing models outperformed the traditional Black–Scholes (B–S) pricing model. Finally, based on the accumulated local effect (ALE) algorithm—which can quantify the impact analysis of different volatilities on pricing models—it was found that the predicted implied volatility using artificial intelligence algorithms was more relevant to the truth. A combination of traditional mathematical models and emerging intelligent algorithms are promoted in this study, providing a reference for investors and risk managers and contributing to the continued development of financial markets. [ABSTRACT FROM AUTHOR]

The performance degradation and degree of damage of bridge materials are more extensive at the fire source compared to other bridge locations. The traditional finite‐element model (FEM) modification method leads to a large error and is unable to achieve a good correction effect. In addition, as the traditional static load test method is used to evaluate the bearing capacities of bridges postfire, the risk of bridge damage, or collapse‐induced by secondary loading—remains unaddressed. To solve these problems, this paper proposes a modified FEM of a bridge following a fire based on the fire dynamics simulator (FDS)–artificial intelligence algorithm. The static behavior of a bridge is predicted using the modified FEM. First, a numerical simulation of a bridge fire is conducted using the FDS to obtain the temperature field distribution and determine the influence ranges of local design parameters of the bridge at the fire source. Second, a response surface model with a high fitting accuracy is constructed to modify the initial FEM by using the artificial intelligence algorithm proxy model together with dynamic load test results for the bridge postfire. Finally, the static behavior is predicted using the updated model. In this study, an actual hollow girder bridge postfire is taken as the research object, and the static behavior prediction results obtained via the proposed method are compared with the static loading test results. The results indicate that the response‐predicted value of the modified FEM is close to the measured value of the bridge postfire. [ABSTRACT FROM AUTHOR]

This manuscript employs a highly efficient artificial intelligence (AI) technique for machine learning (ML) through artificial neural networks (ANNs) and introduces a novel numerical predictive model capable of accurately forecasting the shear capacity of concrete-encased steel (CES) beams. The research begins by conducting shear tests on nine CES beams with high-strength steel, which addresses a significant gap in the shear performance of high-strength steel in CES beams. Subsequently, a comprehensive database of CES beam shear tests is established to train and validate the ANN model. The database consists of 242 sets of test data, compiled from published literature, encompassing a wide range of geometrical and material properties. A sensitivity analysis of the proposed model is then performed using a Pearson chi-square test to determine the relative importance of each input parameter on shear strength. Furthermore, a thorough examination is conducted to assess the impact of each parameter. Finally, the proposed predictive model is compared against current design codes, including ANSI/AISC 360–16 (USA, North America), BS EN 1994-1-1:2004 (Europe), and JGJ 138–2016 (China, Asia). The comparison reveals that ML technology exhibits higher accuracy and robustness in predicting shear bearing capacity. [ABSTRACT FROM AUTHOR]

Background The thrombolytic effect for ischemic stroke (IS) is affected by complex factors, such as acute onset of stroke, short therapeutic time window, various individual patient factors, treatment model, types and doses of medicines as well as mode of administration. To identify the influencing factors of thrombolytic effect, most existing studies adopt statistical methods, while rare studies use artificial intelligence (AI) -based algorithms.Objective To establish models using AI-based algorithms for IS patients based on the real-world data including general patient characteristics, medication model and recovery effects, to achieve precise individualized thrombolytic treatment and provide data support for clinical prescription decisions.Methods A retrospective design was used. The clinical information of IS patients (n=55 621) was extracted from the Yidu Cloud scientific research big data server system of the Second Affiliated Hospital of Dalian Medical University from January 1, 2001 to December 31, 2021, among whom 1 855 with complete information were enrolled according to the inclusion criteria. Thrombolysis effect was evaluated by comparing the National Institutes of Health Stroke Scale (NIHSS) score measured at admission and discharge, and those with an improvement in the NIHSS score by ≥4 points and

Abstract Background 68 Ga-PSMA PET is the leading prostate cancer imaging technique, but the image quality remains noisy and could be further improved using an artificial intelligence-based denoising algorithm. To address this issue, we analyzed the overall quality of reprocessed images compared to standard reconstructions. We also analyzed the diagnostic performances of the different sequences and the impact of the algorithm on lesion intensity and background measures. Methods We retrospectively included 30 patients with biochemical recurrence of prostate cancer who had undergone 68 Ga-PSMA-11 PET-CT. We simulated images produced using only a quarter, half, three-quarters, or all of the acquired data material reprocessed using the SubtlePET® denoising algorithm. Three physicians with different levels of experience blindly analyzed every sequence and then used a 5-level Likert scale to assess the series. The binary criterion of lesion detectability was compared between series. We also compared lesion SUV, background uptake, and diagnostic performances of the series (sensitivity, specificity, accuracy). Results VPFX-derived series were classified differently but better than standard reconstructions (p 0.05). The SubtlePET® algorithm significantly decreased lesion SUV (p

The one-dimensional cutting-stock problem (1D-CSP) consists of obtaining a set of items of different lengths from stocks of one or different lengths, where the minimization of waste is one of the main objectives to be achieved. This problem arises in several industries like wood, glass, and paper, among others similar. Different approaches have been designed to deal with this problem ranging from exact algorithms to hybrid methods of heuristics or metaheuristics. The African Buffalo Optimization (ABO) algorithm is used in this work to address the 1D-CSP. This algorithm has been recently introduced to solve combinatorial problems such as travel salesman and bin packing problems. A procedure was designed to improve the search by taking advantage of the location of the buffaloes just before it is needed to restart the herd, with the aim of not to losing the advance reached in the search. Different instances from the literature were used to test the algorithm. The results show that the developed method is competitive in waste minimization against other heuristics, metaheuristics, and hybrid approaches.

OBJECTIVE: This study aimed to investigate the value of pelvic ultrasound combined with pituitary magnetic resonance imaging (MRI) based on an artificial intelligence algorithm in the diagnosis of girls with central precocious puberty (CPP), providing reference for the prevention and control of CPP in girls. PATIENTS AND METHODS: 75 girls with CPP and 75 normal girls in Nantong First People’s Hospital were studied. Pelvic ultrasound parameters were compared between the two groups based on an artificial intelligence algorithm. Pituitary MRI parameters were analyzed, and pituitary function parameters were explored. RESULTS: The results showed that the diagnostic sensitivity, specificity, and accuracy of the convolutional neural network (CNN) algorithm were 72.3%, 74.6%, and 78.3%, respectively. The sensitivity, specificity, and accuracy of CNN algorithm were significantly higher (p<0.05). The long diameter, anteroposterior diameter, and transverse diameter of the uterus in the precocious puberty (PP) group were significantly larger than those in the normal group (NG). The ovarian long diameter, ovarian anteroposterior diameter, and ovarian transverse diameter in PP group were significantly larger than those in NG. Uterine volume and ovarian volume in PP group were clearly higher than those in NG. The largest follicle diameter was clearly larger in PP patients than in NG patients. The coronal height, coronal width, sagittal height, and sagittal anteroposterior diameter of PP group were clearly higher than those of NG (p<0.05). The sagittal cross-sectional area of pituitary MRI morphology in PP group was significantly greater than that in NG. The pituitary MRI morphology pituitary volume was 272.68 mm in PP group and 191.37 mm in NG, and the pituitary volume was clearly larger in PP group than in NG. The pituitary function parameters estradiol (E2 ), luteinizing hormone (LH) peak, follicle-stimulating hormone (FSH) peak, and LH peak/FSH peak were greater in PP group than in NG. CONCLUSIONS: In summary, the uterine size and ovarian size of girls and the pituitary function index in PP group were larger. Pelvic ultra sound and pituitary MRI indexes can better diagnose CPP and can be widely used in clinical practice with positive diagnostic value. [ABSTRACT FROM AUTHOR]

Abstract Background Dongxiang group, as an important minority, resides in Gansu province which is located at the northwest China, forensic detection system with more loci needed to be studied to improve the application efficiency of forensic case investigation in this group. Methods A 60-plex system including 57 autosomal deletion/insertion polymorphisms (A-DIPs), 2 Y chromosome DIPs (Y-DIPs) and the sex determination locus (Amelogenin) was explored to evaluate the forensic application efficiencies of individual discrimination, kinship analysis and biogeographic origin prediction in Gansu Dongxiang group based on the 60-plex genotype results of 233 unrelated Dongxiang individuals. The 60-plex genotype results of 4582 unrelated individuals from 33 reference populations in five different continents were also collected to analyze the genetic background of Dongxiang group and its genetic relationships with other continental populations. Results The system showed high individual discrimination power, as the cumulative power of discrimination (CPD), cumulative power of exclusion (CPE) for trio and cumulative match probability (CMP) values were 0.99999999999999999999997297, 0.999980 and 2.7029E− 24, respectively. The system could distinguish 98.12%, 93.78%, 82.18%, 62.35% and 39.32% of full sibling pairs from unrelated individual pairs, when the likelihood ratio (LR) limits were set as 1, 10, 100, 1000 and 10,000 based on the simulated family samples, respectively. Additionally, Dongxiang group had the close genetic distances with populations in East Asia, especially showed the intimate genetic relationships with Chinese Han populations, which were concluded from the genetic affinities and genetic background analyses of Dongxiang group and 33 reference populations. In terms of the effectiveness of biogeographic origin inference, different artificial intelligent algorithms possessed different efficacies. Among them, the random forest (RF) and extreme gradient boosting (XGBoost) algorithm models could accurately predict the biogeographic origins of 99.7% and 90.59% of three and five continental individuals, respectively. Conclusion This 60-plex system had good performance for individual discrimination, kinship analysis and biogeographic origin prediction in Dongxiang group, which could be used as a powerful tool for case investigation.

In order to study the application of nonlinear fractional differential equations in computer artificial intelligence algorithms. First, the concept, properties and commonly used neural network models of artificial neural network are introduced, the domestic and foreign status quo of the application of fractional calculus theory to neural network technology is described. Then, the definition, properties and numerical calculation methods of fractional calculus theory are introduced in detail. Then, based on the analysis of artificial intelligence neural network algorithm, the theory of fractional differentiation is introduced, construct BP neural network based on fractional order theory. The Sigmoid function is used as the node function of the neural network, and the actual data is used as the sample set, train a fractional-order network. Finally, by training the network, summarize the change of the two parameters a and p in the function, the impact on the training of the entire network, and make a simple comparison with the fractional order neural network based on the sigmoid function. Experiments show that a variable-order iterative learning algorithm is proposed and applied to the training of neural networks, the results show the feasibility of this algorithm and its advantages in convergence speed and convergence accuracy.