Search Results (20)

Lakes play a crucial role in regional economic development and ecological construction. The variation in lake water depth has a direct impact on local economic activities, such as agriculture, livestock farming, and fisheries, as well as the stability of hydrological conditions and water ecology. In response to the lack of unified evaluation in the application of remote sensing water-depth estimation models for inland lakes, this study systematically compares the performance of numerical models and machine learning models for water-depth estimation in inland lakes. A machine learning-based water-depth estimation model construction methodology suitable for inland lakes is proposed. This study introduces an innovative approach by integrating machine learning techniques with multispectral remote sensing data, improving the accuracy and applicability of water-depth estimation models for inland lakes. The results show the following: (1) The machine learning models based on random forest (RF), BP neural networks (BP), and AdaBoost demonstrate better performance (R² = 0.88, 0.72, and 0.61; MAE = 0.12 m, 0.24 m, and 0.31 m; RMSE = 0.32 m, 0.48 m, and 0.57 m) compared to the multi-band logarithmic ratio (MLR) model (R² = 0.59; MAE = 0.32 m; RMSE = 0.58 m); (2) the machine learning water-depth estimation model constructed based on this methodology exhibits improved precision (R² = 0.92, 0.89, and 0.80; MAE = 0.11 m, 0.17 m, and 0.25 m; RMSE = 0.25 m, 0.30 m, and 0.41 m). This suggests that the methodology is more suitable for the estimation of water depth in medium- and small-sized lakes; (3) The machine learning model developed in this study, combined with multispectral remote sensing imagery, achieves the accuracy required for the evaluation of water depths for practical water resources. This model enables the rapid acquisition of high-precision underwater three-dimensional topographic maps, providing more accurate and timely hydrological data support for lake water resource management. Full article

This paper proposes a novel fault diagnosis methodology for oil-immersed transformers to improve the diagnostic accuracy influenced by gas components in power transformer oil. Firstly, the Random Forest (RF) algorithm is utilized to evaluate and filter the raw data features, solving the problem of determining significant features in the dataset. Secondly, a multi-strategy Improved Particle Swarm Optimization (IPSO) is applied to optimize a double-hidden layer backpropagation neural network (BPNN), which overcomes the challenge of determining hyperparameters in the model. Four enhancement strategies, including SPM chaos mapping based on opposition-based learning, adaptive weight, spiral flight search, and crisscross strategies, are introduced based on traditional Particle Swarm Optimization (PSO) to enhance the model’s optimization capabilities. Lastly, AdaBoost is integrated to fortify the resilience of the IPSO-BP network. Ablation experiments demonstrate an enhanced convergence rate and model accuracy of IPSO. Case analysis using Dissolved Gas Analysis (DGA) samples compares the proposed IPSO–BP–AdaBoost model with other swarm intelligence optimization algorithms integrated with BPNN. The experimental findings highlight the superior diagnostic accuracy and classification performance of the IPSO–BP–AdaBoost model. Full article

As an environmental parameter, the chlorophyll-a concentration (Chl-a) is essential for monitoring water quality and managing the marine ecosystem. However, current mainstream Chl-a inversion algorithms have limited accuracy and poor spatial and temporal generalization in Case II waters. In this study, we constructed a quantitative model for retrieving the spatial and temporal distribution of Chl-a in the Bohai–Yellow Sea area using Geostationary Ocean Color Imager (GOCI) spectral remote sensing reflectance ($R_{rs}\left(\lambda \right)$) products. Firstly, the GOCI $R_{rs}\left(\lambda \right)$ correction model based on measured spectral data was proposed and evaluated. Then, the feature variables of the band combinations with the highest correlation with Chl-a were selected. Subsequently, Chl-a inversion models were developed using three empirical ocean color algorithms (OC4, OC5, and YOC) and four machine learning methods: BP neural network (BPNN), random forest (RF), AdaBoost, and support vector regression (SVR). The retrieval results showed that the machine learning methods were much more accurate than the empirical algorithms and that the RF model retrieved Chl-a with the best performance and the highest prediction accuracy, with a determination coefficient R² of 0.916, a root mean square error (RMSE) of 0.212 mg$·$m⁻³, and a mean absolute percentage error (MAPE) of 14.27%. Finally, the Chl-a distribution in the Bohai–Yellow Sea using the selected RF model was derived and analyzed. Spatially, Chl-a was high in the Bohai Sea, including in Laizhou Bay, Bohai Bay, and Liaodong Bay, with a value higher than 4 mg$·$m⁻³. Chl-a in the Bohai Strait and northern Yellow Sea was relatively low, with a value of less than 3 mg$·$m⁻³. Temporally, the inversion results showed that Chl-a was considerably higher in winter and spring compared to autumn and summer. Diurnal variation retrieval effectively demonstrated GOCI’s potential as a capable tool for monitoring intraday changes in chlorophyll-a concentrations. Full article

Nowadays, it has become a trend to use finite element simulation instead of experimental processes, and this is widely used in the fields of structural mechanics, fluid mechanics, fracture mechanics, and so on. By replacing the experimental process with finite element simulation, we can reduce time and costs; however, when using finite element simulation, we need to define a series of settings, such as modeling, material assignment, environment settings, and many other operations. For laser shock processing intensification, the simulation experiment process is cumbersome and time-consuming. It involves performing neural network agent modeling, replacing finite element simulation with the learning and prediction capabilities of neural networks, learning by using some of the simulation results as a training sets for the neural network, and then learning by using the remaining simulation results as testing sets to test the predictive ability of the neural network agent model. TC4 titanium alloy was selected as the experimental material. Three kinds of neural network agent models, a genetic algorithm-optimized BP network, a strong classifier design based on BP_Adaboost, and an extreme learning machine, instead of finite element simulation experiments, were used to predict the residual stresses generated on the surfaces of the material under different laser shock parameters. Comparing the prediction performances of different neural network agent models, the genetic algorithm-optimized BP network shows the best prediction performance, and its prediction value matches well with the experimental value. The R², RMSE, and MAE of the testing sets of the BP network optimized using the genetic algorithm were 0.9985, 44.4518, and 30.6285, respectively. The BP network agent model optimized using the genetic algorithm for laser shock parameters other than the 208 sets of data also had good prediction performance, and the predicted values were similar to the actual experimental results. The prediction results show that the BP network optimized using the genetic algorithm can predict the residual stresses on the surface of TC4 titanium alloy material under strengthening via laser shock processing; the genetic algorithm-optimized BP neural network agent model is more convenient and quicker compared to the finite element simulation, and the predicted value is also similar to the actual value. It can thus be used to replace finite element simulation by establishing a more convenient and quicker neural network agent model. Full article

Medium-term hydrological streamflow forecasting can guide water dispatching departments to arrange the discharge and output plan of hydropower stations in advance, which is of great significance for improving the utilization of hydropower energy and has been a research hotspot in the field of hydrology. However, the distribution of water resources is uneven in time and space. It is important to predict streamflow in advance for the rational use of water resources. In this study, a Bayesian model average integrated prediction method is proposed, which combines artificial intelligence algorithms, including long-and short-term memory neural network (LSTM), gate recurrent unit neural network (GRU), recurrent neural network (RNN), back propagation (BP) neural network, multiple linear regression (MLR), random forest regression (RFR), AdaBoost regression (ABR) and support vector regression (SVR). In particular, the simulated annealing (SA) algorithm is used to optimize the hyperparameters of the model. The practical application of the proposed model in the ten-day scale inflow prediction of the Three Gorges Reservoir shows that the proposed model has good prediction performance; the Nash–Sutcliffe efficiency NSE is 0.876, and the correlation coefficient r is 0.936, which proves the accuracy of the model. Full article

Building electricity load forecasting plays an important role in building energy management, peak demand and power grid security. In the past two decades, a large number of data-driven models have been applied to building and larger-scale energy consumption predictions. Although these models have been successful in specific cases, their performances would be greatly affected by the quantity and quality of the building data. Moreover, for older buildings with sparse data, or new buildings with no historical data, accurate predictions are difficult to achieve. Aiming at such a data silos problem caused by the insufficient data collection in the building energy consumption prediction, this study proposes a building electricity load forecasting method based on a similarity judgement and an improved TrAdaBoost algorithm (iTrAdaBoost). The Maximum Mean Discrepancy (MMD) is used to search similar building samples related to the target building from public datasets. Different from general Boosting algorithms, the proposed iTrAdaBoost algorithm iteratively updates the weights of the similar building samples and combines them together with the target building samples for a prediction accuracy improvement. An educational building’s case study is carried out in this paper. The results show that even when the target and source samples belong to different domains, i.e., the geographical location and meteorological condition of the buildings are different, the proposed MMD-iTradaBoost method has a better prediction accuracy in the transfer learning process than the BP or traditional AdaBoost models. In addition, compared with other advanced deep learning models, the proposed method has a simple structure and is easy for engineering implementation. Full article

The problem of air pollution has attracted more and more attention. PM_2.5 is a key factor affecting air quality. In order to improve the prediction accuracy of PM_2.5 concentration and make people effectively control the generation and propagation of atmospheric pollutants, in this paper, a long short-term memory neural network (LSTM) model based on principal component analysis (PCA) and attention mechanism (attention) is constructed, which first uses PCA to reduce the dimension of data, eliminate the correlation effect between indicators, and reduce model complexity, and then uses the extracted principal components to establish a PCA-attention-LSTM model. Simulation experiments were conducted on the air pollutant data, meteorological element data, and working day data of five cities in Ningxia from 2018 to 2020 to predict the PM_2.5 concentration. The PCA-attention-LSTM model is compared with the support vector regression model (SVR), AdaBoost model, random forest model (RF), BP neural network model (BPNN), and long short-term memory neural network (LSTM). The results show that the PCA-attention-LSTM model is optimal; the correlation coefficients of the PCA-attention-LSTM model in Wuzhong, Yinchuan, Zhongwei, Shizuishan, and Guyuan are 0.91, 0.93, 0.91, 0.91, and 0.90, respectively, and the SVR model is the worst. The addition of variables such as a week, precipitation, and temperature can better predict PM_2.5 concentration. The concentration of PM_2.5 was significantly correlated with the geographical location of the municipal area, and the overall air quality of the southern mountainous area was better than that in the northern Yellow River irrigation area. PM_2.5 concentration shows a clear seasonal change trend, with the lowest in summer and the highest in winter, which is closely related to the climate environment of Ningxia. Full article

Electrical apparatuses are prone to faults, which generally causes fires. During such fires, the identification of resolidified copper beads on wires has a strong influence on the direction of the fire investigation. There are four kinds of resolidified beads formed on copper conductors that have been through the fire with and without voltage, namely, ‘cause’ beads (CB), ‘victim’ beads (VB), overload globules (OG), and fire melting globules (FG). First, to improve the identification’s objectivity and quantifiability, we used various morphologic parameters of crystals and porosities to express metallurgical microcharacteristics, such as Ar-G, As-G, An-G, Dm-G, R-G, FD-G, Fm-G, Ar-G, As-P, An-P, Dm-P, R-P, FD-P, Fm-P, P3-P, and Cu₂O. Then, several machine learning classifiers were developed to predict the melted beads based on metallurgical morphologic parameters by using SVM, BP neutral network (BPNN), AdaBoost, bagging, and random forest (RF), respectively. Models were trained and tested based on the sample set, consisting of 560 samples which were collected from real room fires. ACC/F1 of the RF model were 0.894/0.805, respectively, which are superior to SVM, BPNN, AdaBoost, and bagging. For the RF classifier, the recall rates of CB, VB, OG, and FG were 92.5%, 67.5%, 100%, and 97.5%, respectively, indicating that RF has best potential to predict OG and FG. The variable importance was analyzed to distinguish key features, and the results revealed that Cu₂O has highest impact on bead classification. We cannot find much promise with this method that uses multiple metallurgical and morphological parameters for distinguishing between CB and VB. It is confirmed that no machine learning classifiers combined with metallurgical analysis could do this work well in this paper. Thus, we strongly recommend that other evidence for investigation in the room fire should also be considered to cover the shortage of this kind. Full article

Fatigue driving has always received a lot of attention, but few studies have focused on the fact that human fatigue is a cumulative process over time, and there are no models available to reflect this phenomenon. Furthermore, the problem of incorrect detection due to facial expression is still not well addressed. In this article, a model based on BP neural network and time cumulative effect was proposed to solve these problems. Experimental data were used to carry out this work and validate the proposed method. Firstly, the Adaboost algorithm was applied to detect faces, and the Kalman filter algorithm was used to trace the face movement. Then, a cascade regression tree-based method was used to detect the 68 facial landmarks and an improved method combining key points and image processing was adopted to calculate the eye aspect ratio (EAR). After that, a BP neural network model was developed and trained by selecting three characteristics: the longest period of continuous eye closure, number of yawns, and percentage of eye closure time (PERCLOS), and then the detection results without and with facial expressions were discussed and analyzed. Finally, by introducing the Sigmoid function, a fatigue detection model considering the time accumulation effect was established, and the drivers’ fatigue state was identified segment by segment through the recorded video. Compared with the traditional BP neural network model, the detection accuracies of the proposed model without and with facial expressions increased by 3.3% and 8.4%, respectively. The number of incorrect detections in the awake state also decreased obviously. The experimental results show that the proposed model can effectively filter out incorrect detections caused by facial expressions and truly reflect that driver fatigue is a time accumulating process. Full article

Accurate load forecasting is an important issue for the reliable and efficient operation of a power system. In this study, a hybrid algorithm (EMDIA) that combines empirical mode decomposition (EMD), isometric mapping (Isomap), and Adaboost to construct a prediction mode for mid- to long-term load forecasting is developed. Based on full consideration of the meteorological and economic factors affecting the power load trend, the EMD method is used to decompose the load and its influencing factors into multiple intrinsic mode functions (IMF) and residuals. Through correlation analysis, the power load is divided into fluctuation term and trend term. Then, the key influencing factors of feature sequences are extracted by Isomap to eliminate the correlations and redundancy of the original multidimensional sequences and reduce the dimension of model input. Eventually, the Adaboost prediction method is adopted to realize the prediction of the electrical load. In comparison with the RF, LSTM, GRU, BP, and single Adaboost method, the prediction obtained by this proposed model has higher accuracy in the mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and determination coefficient (R²). Compared with the single Adaboost algorithm, the EMDIA reduces MAE by 11.58, MAPE by 0.13%, and RMSE by 49.93 and increases R² by 0.04. Full article

Experts usually inspect electroencephalogram (EEG) recordings page-by-page in order to identify epileptic seizures, which leads to heavy workloads and is time consuming. However, the efficient extraction and effective selection of informative EEG features is crucial in assisting clinicians to diagnose epilepsy accurately. In this paper, a determinant of covariance matrix (Cov–Det) model is suggested for reducing EEG dimensionality. First, EEG signals are segmented into intervals using a sliding window technique. Then, Cov–Det is applied to each interval. To construct a features vector, a set of statistical features are extracted from each interval. To eliminate redundant features, the Kolmogorov–Smirnov (KST) and Mann–Whitney U (MWUT) tests are integrated, the extracted features ranked based on KST and MWUT metrics, and arithmetic operators are adopted to construe the most pertinent classified features for each pair in the EEG signal group. The selected features are then fed into the proposed AdaBoost Back-Propagation neural network (AB_BP_NN) to effectively classify EEG signals into seizure and free seizure segments. Finally, the AB_BP_NN is compared with several classical machine learning techniques; the results demonstrate that the proposed mode of AB_BP_NN provides insignificant false positive rates, simpler design, and robustness in classifying epileptic signals. Two datasets, the Bern–Barcelona and Bonn datasets, are used for performance evaluation. The proposed technique achieved an average accuracy of 100% and 98.86%, respectively, for the Bern–Barcelona and Bonn datasets, which is considered a noteworthy improvement compared to the current state-of-the-art methods. Full article

Different cultivars of pear trees are often planted in one orchard to enhance yield for its gametophytic self-incompatibility. Therefore, an accurate and robust modelling method is needed for the non-destructive determination of leaf nitrogen (N) concentration in pear orchards with mixed cultivars. This study proposes a new technique based on in-field visible-near infrared (VIS-NIR) spectroscopy and the Adaboost algorithm initiated with machine learning methods. The performance was evaluated by estimating leaf N concentration for a total of 1285 samples from different cultivars, growth regions, and tree ages and compared with traditional techniques, including vegetation indices, partial least squares regression, singular support vector regression (SVR) and neural networks (NN). The results demonstrated that the leaf reflectance responded to the leaf nitrogen concentration were more sensitive to the types of cultivars than to the different growing regions and tree ages. Moreover, the AdaBoost.RT-BP had the best accuracy in both the training (R² = 0.96, root mean relative error (RMSE) = 1.03 g kg⁻¹) and the test datasets (R² = 0.91, RMSE = 1.29 g kg⁻¹), and was the most robust in repeated experiments. This study provides a new insight for monitoring the status of pear trees by the in-field VIS-NIR spectroscopy for better N managements in heterogeneous pear orchards. Full article

This study offers an efficient hardness identification approach to address the problem of poor real-time performance and accuracy in coal and rock hardness detection. To begin, Ensemble Empirical Mode Decomposition (EEMD) was performed on the current signal of the cutting motor to obtain a number of Intrinsic Mode Functions (IMFs). Further, the target signal was selected among the IMFs to reconstruct the current signal according to the energy density and correlation coefficient criteria. After that, the Multi-scale Permutation Entropy (MPE) of the reconstructed signal was trained by the Adaboost improved Back Propagation (BP) neural network, in order to establish the hardness recognition model. Finally, the cutting arm’s swing speed and the cutting head’s rotation speed were adjusted based on the coal and rock hardness. The simulation results indicated that using the energy density and correlation criterion to reconstruct the signal can successfully filter out noise interference. Compared to the BP model, the relative root-mean-square error of the Adaboost-BP model decreased by 0.0633, and the prediction results were more accurate. Additionally, the speed control strategy based on coal and rock hardness can ensure the efficient cutting of the roadheader. Full article

In order to reduce some of the problems of technological restructuring and insufficient expansion in the current film and television production mode, the application of emerging technologies such as artificial intelligence (AI), virtual reality (VR), and Internet of Things (IoT) in the film and television industry is introduced in this research. First, a topical crawler tool was constructed to grab relevant texts about “AI”, “VR”, and “IoT” crossover “film and television”, and the grasping accuracy rate and recall rate of this tool were compared. Then, based on the extracted text, the data of recent development in related fields were extracted. The AdaBoost algorithm was used to improve the BP (Back Propagation) neural network (BPNN). This model was used to predict the future development scale of related fields. Finally, a virtual character interaction system based on IoT-sensor technology was built and its performance was tested. The results showed that the topical crawler tool constructed in this study had higher recall rate and accuracy than other tools, and a total of 188 texts related to AI, VR, and IoT crossover television films were selected after Naive Bayes classification. In addition, the error of the BPNN prediction model based on the AdaBoost algorithm was less than 20%, and it can effectively predict the future development scale of AI and other fields. In addition, the virtual character interaction system based on IoT technology constructed in this study has a high motion recognition rate, produces a strong sense of immersion among users, and can realize real-time capture and imitation of character movements. In a word, the field of AI and VR crossover film and television has great development prospects in the future. Therefore, the application of IoT technology in building the virtual-character interaction system can improve the effect of VR or AI film and television production. Full article

To deal with the influence of temperature drift for a Micro-Electro-Mechanical System (MEMS) gyroscope, this paper proposes a new temperature error parallel processing method based on a novel fusion algorithm. Firstly, immune based particle swarm optimization (IPSO) is employed for optimal parameters search for Variational Modal Decomposition (VMD). Then, we can get the optimal decomposition parameters, wherein permutation entropy (PE) is employed as the fitness function of the particles. Then, the improved VMD is performed on the output signal of the gyro to obtain intrinsic mode functions (IMFs). After judging by sample entropy (SE), the IMFs are divided into three categories: noise term, mixed term and feature term, which are processed differently. Filter the mixed term and compensate the feature term at the same time. Finally, reconstruct them and get the result. Compared with other optimization algorithms, IPSO has a stronger global search ability and faster convergence speed. After Back propagation neural network (BP) is enhanced by Adaptive boosting (Adaboost), it becomes a strong learner and a better model, which can approach the real value with higher precision. The experimental result shows that the novel parallel method proposed in this paper can effectively solve the problem of temperature errors. Full article