Search Results (805)

This study explored the performance and reliability of three predictive models—extreme gradient boosting (XGB), convolutional neural network (CNN), and residual neural network (ResNet)—for determining the moisture content in Porphyra yezoensis using near-infrared (NIR) spectroscopy. We meticulously selected 380 samples from various sources to ensure a comprehensive dataset, which was then divided into training (300 samples) and test sets (80 samples). The models were evaluated based on prediction accuracy and stability, employing genetic algorithms (GA) and partial least squares (PLS) for wavelength selection to enhance the interpretability of feature extraction outcomes. The results demonstrated that the XGB model excelled with a determination coefficient (R²) of 0.979, a root mean square error of prediction (RMSEP) of 0.004, and a high ratio of performance to deviation (RPD) of 4.849, outperforming both CNN and ResNet models. A Gaussian process regression (GPR) was employed for uncertainty assessment, reinforcing the reliability of our models. Considering the XGB model’s high accuracy and stability, its implementation in industrial settings for quality assurance is recommended, particularly in the food industry where rapid and non-destructive moisture content analysis is essential. This approach facilitates a more efficient process for determining moisture content, thereby enhancing product quality and safety. Full article

Lactic acid content is a crucial indicator for evaluating maize silage quality, and its accurate detection is essential for ensuring product quality. In this study, a quantitative prediction model for the change of lactic acid content during the secondary fermentation of maize silage was constructed based on a colorimetric sensor array (CSA) combined with hyperspectral imaging. Volatile odor information from maize silage samples with different days of aerobic exposure was obtained using CSA and recorded by a hyperspectral imaging (HSI) system. Subsequently, the acquired spectral data were subjected to preprocessing through five distinct methods before being modeled using partial least squares regression (PLSR). The coronavirus herd immunity optimizer (CHIO) algorithm was introduced to screen three color-sensitive dyes that are more sensitive to changes in lactic acid content of maize silage. To minimize model redundancy, three algorithms, such as competitive adaptive reweighted sampling (CARS), were used to extract the characteristic wavelengths of the three dyes, and the combination of the characteristic wavelengths obtained by each algorithm was used as an input variable to build an analytical model for quantitative prediction of the lactic acid content by support vector regression (SVR). Moreover, two optimization algorithms, namely grid search (GS) and crested porcupine optimizer (CPO), were compared to determine their effectiveness in optimizing the parameters of the SVR model. The results showed that the prediction accuracy of the model can be significantly improved by choosing appropriate pretreatment methods for different color-sensitive dyes. The CARS-CPO-SVR model had better prediction, with a prediction set determination coefficient ($R_P^2$), root mean square error of prediction (RMSEP), and a ratio of performance to deviation (RPD) of 0.9617, 2.0057, and 5.1997, respectively. These comprehensive findings confirm the viability of integrating CSA with hyperspectral imaging to accurately quantify the lactic acid content in silage, providing a scientific and novel method for maize silage quality testing. Full article

Correct design of the sheet metal forming process requires knowledge of the friction phenomenon occurring in various areas of the drawpiece. Additionally, the friction at the drawbead is decisive to ensure that the sheet flows in the desired direction. This article presents the results of experimental tests enabling the determination of the coefficient of friction at the drawbead and using a specially designed tribometer. The test material was a DC04 carbon steel sheet. The tests were carried out for different orientations of the samples in relation to the sheet rolling direction, different drawbead heights, different lubrication conditions and different average roughnesses of the countersamples. According to the aim of this work, the Features Importance analysis, conducted using the Gradient-Boosted Regression Trees algorithm, was used to find the influence of several parameter features on the coefficient of friction. The advantage of gradient-boosted decision trees is their ability to analyze complex relationships in the data and protect against overfitting. Another advantage is that there is no need for prior data processing. According to the best of the authors’ knowledge, the effectiveness of gradient-boosted decision trees in analyzing the friction occurring in the drawbead in sheet metal forming has not been previously studied. To improve the accuracy of the model, five MinLeafs were applied to the regression tree, together with 500 ensembles utilized for learning the previously learned nodes, noting that the MinLeaf indicates the minimum number of leaf node observations. The least-squares-boosting technique, often known as LSBoost, is used to train a group of regression trees. Features Importance analysis has shown that the friction conditions (dry friction of lubricated conditions) had the most significant influence on the coefficient of friction, at 56.98%, followed by the drawbead height, at 23.41%, and the sample width, at 11.95%. The average surface roughness of rollers and sample orientation have the smallest impact on the value of the coefficient of friction at 6.09% and 1.57%, respectively. The dispersion and deviation observed for the testing dataset from the experimental data indicate the model’s ability to predict the values of the coefficient of friction at a coefficient of determination of R² = 0.972 and a mean-squared error of MSE = 0.000048. It was qualitatively found that in order to ensure the optimal (the lowest) coefficient of friction, it is necessary to control the friction conditions (use of lubricant) and the drawbead height. Full article

Updated and accurate crop yield maps play a key role in the agricultural environment. Their application enables the support for sustainable agricultural practices and the formulation of effective strategies to mitigate the impacts of climate change. Farmers can apply the maps to gain an overview of the yield variability, improving farm management practices and optimizing inputs to increase productivity and sustainability such as fertilizers. Earth observation (EO) data make it possible to map crop yield estimations over large areas, although this will remain challenging for specific crops such as sugarcane. Yield data collection is an expensive and time-consuming practice that often limits the number of samples collected. In this study, the sugarcane yield estimation based on a small number of training datasets within smallholder crop systems in the Tha Khan Tho District, Thailand for the year 2022 was assessed. Specifically, multi-temporal satellite datasets from multiple sensors, including Sentinel-2 and Landsat 8/9, were involved. Moreover, in order to generate the sugarcane yield estimation maps, only 75 sampling plots were selected and surveyed to provide training and validation data for several powerful machine-learning algorithms, including multiple linear regression (MLR), stepwise multiple regression (SMR), partial least squares regression (PLS), random forest regression (RFR), and support vector regression (SVR). Among these algorithms, the RFR model demonstrated outstanding performance, yielding an excellent result compared to existing techniques, achieving an R-squared (R²) value of 0.79 and a root mean square error (RMSE) of 3.93 t/ha (per 10 m × 10 m pixel). Furthermore, the mapped yields across the region closely aligned with the official statistical data from the Office of the Cane and Sugar Board (with a range value of 36,000 ton). Finally, the sugarcane yield estimation model was applied to over 2100 sugarcane fields in order to provide an overview of the current state of the yield and total production in the area. In this work, the different yield rates at the field level were highlighted, providing a powerful workflow for mapping sugarcane yields across large regions, supporting sugarcane crop management and facilitating decision-making processes. Full article

Due to its advantages such as speed and noninvasive nature, near-infrared spectroscopy (NIRS) technology has been widely used in detecting the nutritional content of nut food. This study aims to address the problem of offline quantitative analysis models producing unsatisfactory results for different batches of samples due to complex and unquantifiable factors such as storage conditions and origin differences of Korean pine nuts. Based on the offline model, an online learning model was proposed using recursive partial least squares (RPLS) regression with online multiplicative scatter correction (OMSC) preprocessing. This approach enables online updates of the original detection model using a small amount of sample data, thereby improving its generalization ability. The OMSC algorithm reduces the prediction error caused by the inability to perform effective scatter correction on the updated dataset. The uninformative variable elimination (UVE) algorithm appropriately increases the number of selected feature bands during the model updating process to expand the range of potentially relevant features. The final model is iteratively obtained by combining new sample feature data with RPLS. The results show that, after OMSC preprocessing, with the number of features increased to 100, the new online model’s $R^2$ value for the prediction set is 0.8945. The root mean square error of prediction (RMSEP) is 3.5964, significantly outperforming the offline model, which yields values of 0.4525 and 24.6543, respectively. This indicates that the online model has dynamic and sustainable characteristics that closely approximate practical detection, and it provides technical references and methodologies for the design and development of detection systems. It also offers an environmentally friendly tool for rapid on-site analysis for nut food regulatory agencies and production enterprises. Full article

Industrial computed tomography (CT) is widely used in the measurement field owing to its advantages such as non-contact and high precision. To obtain accurate size parameters, fitting parameters can be obtained rapidly by processing volume data in the form of point clouds. However, due to factors such as artifacts in the CT reconstruction process, many abnormal interference points exist in the point clouds obtained after segmentation. The classic least squares algorithm is easily affected by these points, resulting in significant deviation of the solution of linear equations from the normal value and poor robustness, while the random sample consensus (RANSAC) approach has insufficient fitting accuracy within a limited timeframe and the number of iterations. To address these shortcomings, we propose a spherical point cloud fitting algorithm based on projection filtering and K-Means clustering (PK-RANSAC), which strategically integrates and enhances these two methods to achieve excellent accuracy and robustness. The proposed method first uses RANSAC for rough parameter estimation, then corrects the deviation of the spherical center coordinates through two-dimensional projection, and finally obtains the spherical center point set by sampling and performing K-Means clustering. The largest cluster is weighted to obtain accurate fitting parameters. We conducted a comparative experiment using a three-dimensional ball-plate standard. The sphere center fitting deviation of PK-RANSAC was 1.91 μm, which is significantly better than RANSAC’s value of 25.41 μm. The experimental results demonstrate that PK-RANSAC has higher accuracy and stronger robustness for fitting geometric parameters. Full article

An accurate estimation of the state of health (SOH) of Li-ion batteries is critical for the efficient and safe operation of battery-powered systems. Traditional methods for SOH estimation, such as Coulomb counting, often struggle with sensitivity to measurement noise and time-consuming tests. This study addresses this issue by combining incremental capacity (IC) analysis and a novel neural network, Kolmogorov–Arnold Networks (KANs). Fifteen features were extracted from IC curves and a 2RC equivalent circuit model was used to identify the internal resistance of batteries. Recursive least squares were used to identify the parameters of the equivalent circuit model. IC features and internal resistance were considered as input variables to establish the SOH estimation model. Three commonly used machine learning methods (BP, LSTM, TCN) and two hybrid algorithms (LSTM-KAN and TCN-KAN) were used to establish the SOH estimation model. The performance of the five models was compared and analyzed. The results demonstrated that the hybrid models integrated with the KAN performed better than the conventional models, and the LSTM-KAN model had higher estimation accuracy than that of the other models. The model achieved a mean absolute error of less than 0.412% in SOH prediction in the test and validation dataset. The proposed model does not require complete charge and discharge data, which provides a promising tool for the accurate monitoring and fast detection of battery SOH. Full article

Receiving uninterrupted videos from a scene with multiple cameras is a challenging task. One of the issues that significantly affects this task is called occlusion. In this paper, we propose an algorithm for occlusion handling in multi-camera systems. The proposed algorithm, which is called Real-time leader finder (Releaf), leverages mechanism design to assign leader and follower roles to each of the cameras in a multi-camera setup. We assign leader and follower roles to the cameras and lead the motion by the camera with the least occluded view using the Stackelberg equilibrium. The proposed approach is evaluated on our previously open-sourced tendon-driven 3D-printed robotic eye that tracks the face of a human subject. Experimental results demonstrate the superiority of the proposed algorithm over the Q-leaning and Deep Q Networks (DQN) baselines, achieving an improvement of $20\%$ and $18\%$ for horizontal errors and an enhancement of $81\%$ for vertical errors, as measured by the root mean squared error metric. Furthermore, Releaf has the superiority of real-time performance, which removes the need for training and makes it a promising approach for occlusion handling in multi-camera systems. Full article

The accurate prediction of carbon dioxide (CO₂) emissions in the building industry can provide data support and theoretical insights for sustainable development. This study proposes a hybrid model for predicting CO₂ emissions that combines a multi-strategy improved particle swarm optimization (MSPSO) algorithm with a long short-term memory (LSTM) model. Firstly, the particle swarm optimization (PSO) algorithm is enhanced by combining tent chaotic mapping, mutation for the least-fit particles, and a random perturbation strategy. Subsequently, the performance of the MSPSO algorithm is evaluated using a set of 23 internationally recognized test functions. Finally, the predictive performance of the MSPSO-LSTM hybrid model is assessed using data from the building industry in the Yangtze River Delta region as a case study. The results indicate that the coefficient of determination (R²) of the model reaches 0.9677, which is more than 10% higher than that of BP, LSTM, and CNN non-hybrid models and demonstrates significant advantages over PSO-LSTM, GWO-LSTM, and WOA-LSTM hybrid models. Additionally, the mean square error (MSE) of the model is 2445.6866 Mt, and the mean absolute error (MAE) is 4.1010 Mt, both significantly lower than those of the BP, LSTM, and CNN non-hybrid models. Overall, the MSPSO-LSTM hybrid model demonstrates high predictive accuracy for CO₂ emissions in the building industry, offering robust support for the sustainable development of the industry. Full article

Time-varying underwater acoustic (UWA) channels are the key challenge of underwater acoustic communication (UAC). Although UAC exhibits time-variance characteristics significantly in time domains, its delay-Doppler (DD) domain representation tends to be time-invariant. Orthogonal time–frequency space (OTFS) modulation has recently been proposed and has acquired widespread interest due to its excellent performance over time-varying channels. In the UWA OTFS system, the novel DD domain channel estimation algorithm that employs a multidirectional adaptive moving average scheme is proposed. Specifically, the proposed scheme is cascaded by a channel estimator and moving average filter. The channel estimator can be employed to estimate the time-invariant channel of the DD domain multidirectionally, improving proportionate normalized least mean squares (IPNLMS). Meanwhile, the moving average filter is used to reduce the output noise of the IPNLMS. The performance of the proposed method is verified by simulation experiments and real-world lake experiments. The results demonstrate that the proposed channel estimation method can outperform those of benchmark algorithms. Full article

In precision agriculture, after vegetable transplanters plant the seedlings, field management during the seedling stage is necessary to optimize the vegetable yield. Accurately identifying and extracting the centerlines of crop rows during the seedling stage is crucial for achieving the autonomous navigation of robots. However, the transplanted ridges often experience missing seedling rows. Additionally, due to the limited computational resources of field agricultural robots, a more lightweight navigation line fitting algorithm is required. To address these issues, this study focuses on mid-to-high ridges planted with double-row vegetables and develops a seedling band-based navigation line extraction model, a Seedling Navigation Convolutional Neural Network (SN-CNN). Firstly, we proposed the C2f_UIB module, which effectively reduces redundant computations by integrating Network Architecture Search (NAS) technologies, thus improving the model’s efficiency. Additionally, the model incorporates the Simplified Attention Mechanism (SimAM) in the neck section, enhancing the focus on hard-to-recognize samples. The experimental results demonstrate that the proposed SN-CNN model outperforms YOLOv5s, YOLOv7-tiny, YOLOv8n, and YOLOv8s in terms of the model parameters and accuracy. The SN-CNN model has a parameter count of only 2.37 M and achieves an [email protected] of 94.6%. Compared to the baseline model, the parameter count is reduced by 28.4%, and the accuracy is improved by 2%. Finally, for practical deployment, the SN-CNN algorithm was implemented on the NVIDIA Jetson AGX Xavier, an embedded computing platform, to evaluate its real-time performance in navigation line fitting. We compared two fitting methods: Random Sample Consensus (RANSAC) and least squares (LS), using 100 images (50 test images and 50 field-collected images) to assess the accuracy and processing speed. The RANSAC method achieved a root mean square error (RMSE) of 5.7 pixels and a processing time of 25 milliseconds per image, demonstrating a superior fitting accuracy, while meeting the real-time requirements for navigation line detection. This performance highlights the potential of the SN-CNN model as an effective solution for autonomous navigation in field cross-ridge walking robots. Full article

In zinc smelting solution, because the concentration of zinc is too high, the spectral signals of trace copper are masked by the spectral signals of zinc, and their spectral signals overlap, which makes it difficult to detect the concentration of trace copper. To solve this problem, a spectrophotometric method based on integrated and partition modeling is proposed. Firstly, the derivative spectra based on continuous wavelet transform are used to preprocess the spectral signal and highlight the spectral peak of copper. Then, the interval partition modeling is used to select the optimal characteristic interval of copper according to the root mean square error of prediction, and the wavelength points of the absorbance matrix are selected by correlation-coefficient threshold to improve the sensitivity and linearity of copper ions. Finally, the partial least squares integrated modeling based on the Adaboost algorithm is established by using the selected wavelength to realize the concentration detection of trace copper in the zinc liquid. Comparing the proposed method with existing regression methods, the results showed that this method can not only reduce the complexity of wavelength screening, but can also ensure the stability of detection performance. The predicted root mean square error of copper was 0.0307, the correlation coefficient was 0.9978, and the average relative error of prediction was 3.14%, which effectively realized the detection of trace copper under the background of high-concentration zinc liquid. Full article

In this work, we resolve the cascaded channel estimation problem and the reflected channel estimation problem for the reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmWave) systems. The novel two-step method contains modified multiple population genetic algorithm (MMPGA), least squares (LS), residual network (ResNet), and multi-task regression model. In the first step, the proposed MMPGA-LS optimizes the crossover strategy and mutation strategy. Besides, the ResNet achieves cascaded channel estimation by learning the relationship between the cascaded channel obtained by the MMPGA-LS and the channel of the user (UE)-RIS-base station (BS). Then, the proposed multi-task-ResNet (MTRnet) is introduced for the reflected channel estimation. Relying on the output of ResNet, the MTRnet with multiple output layers estimates the coefficients of reflected channels and reconstructs the channel of UE-RIS and RIS-BS. Remarkably, the proposed MTRnet is capable of using a lower optimization model to estimate multiple reflected channels compared with the classical neural network with the single output layer. A series of experimental results validate the superiority of the proposed method in terms of a lower norm mean square error (NMSE). Besides, the proposed method also obtains a low NMSE in the RIS with the formulation of the uniform planar array. Full article

To establish ubiquitous and energy-efficient wireless sensor networks (WSNs), short-range Internet of Things (IoT) devices require Bluetooth low energy (BLE) technology, which functions at 2.4 GHz. This study presents a novel approach as follows: a fully integrated all-digital phase-locked loop (ADPLL)-based Gaussian frequency shift keying (GFSK) modulator incorporating two-point modulation (TPM). The modulator aims to enhance the efficiency of BLE communication in these networks. The design includes a time-to-digital converter (TDC) with the following three key features to improve linearity and time resolution: fast settling time, low dropout regulators (LDOs) that adapt to process, voltage, and temperature (PVT) variations, and interpolation assisted by an analog-to-digital converter (ADC). It features a digital controlled oscillator (DCO) with two key enhancements as follows: ΔΣ modulator dithering and hierarchical capacitive banks, which expand the frequency tuning range and improve linearity, and an integrated, fast-converging least-mean-square (LMS) algorithm for DCO gain calibration, which ensures compliance with BLE 5.0 stable modulation index (SMI) requirements. Implemented in a 28 nm CMOS process, occupying an active area of 0.33 mm², the modulator demonstrates a wide frequency tuning range of from 2.21 to 2.58 GHz, in-band phase noise of −102.1 dBc/Hz, and FSK error of 1.42% while consuming 1.6 mW. Full article

Due to the scarcity of modeling samples and the low prediction accuracy of the matte grade prediction model in the copper melting process, a new prediction method is proposed. This method is based on enhanced generative adversarial networks (EGANs) and random forests (RFs). Firstly, the maximum relevance minimum redundancy (MRMR) algorithm is utilized to screen the key influencing factors of matte grade and remove redundant information. Secondly, the GAN data augmentation model containing different activation functions is constructed. And, the generated data fusion criterion based on the root mean squared error (RMSE) and the coefficient of determination (R²) is designed, which can tap into the global character distributions of the copper melting data to improve the quality of the generated data. Finally, a matte grade prediction model based on RF is constructed, and the industrial data collected from the copper smelting process are used to verify the effectiveness of the model. The experimental results show that the proposed method can obtain high-quality generated data, and the prediction accuracy is better than other models. The R² is improved by at least 2.68%, and other indicators such as RMSE, mean absolute error (MAE), and mean absolute percentage error (MAPE) are significantly improved. Full article