Percent Relative Deviation Research Articles

Estimation of soil water and organic matter content in medium and low yield fields of Ningxia Yellow River Irrigation area based on hyperspectral information.

Accurately obtaining soil water and organic matter content is of great significance for improving soil qua-lity in croplands with medium to low yield. We explored the estimation effect of fractional order differentiation (FOD) combined with different spectral indices on soil water and organic matter content in medium and low yield croplands of Ningxia Yellow River Irrigation Area. After root mean square transformation of field measured hyperspectral reflectance, we used 0-2 FOD (with a step length of 0.25) to construct difference index (DI), ratio index (RI), product index (PI), sum index (SI), generalized difference index (GDI), and nitrogen planar domain index (NPDI) and to select the optimal spectral index based on the correlation coefficients between six spectral indices with soil water and organic matter contents. We constructed a model for estimating soil water and organic matter content based on partial least squares regression (PLSR) and support vector machine (SVM). The results showed that the correlation between soil water and organic matter content and spectral information was effectively improved after FOD transformation compared with the original spectrum, with maximum increases of 0.1785 and 0.1713, respectively. The soil water content sensitive bands were mainly in the range of 400-630 and 1350-1940 nm, while the sensitive bands of organic matter content were mainly at 460-850, 1530-1910, and 2060-2310 nm. The accuracy of SVM model was significantly higher than that of PLSR, and the soil water content estimation model based on 1.75-order NPDI-SVM reached the highest precision, with a validation determination coefficient (Rp2) of 0.970, root mean square error (RMSE) of 1.615, and relative percent deviation (RPD) of 4.211. The organic matter content estimation model based on 0.5 order DI-SVM had the best performance, with Rp2, RMSE and RPD of 0.983, 0.701 and 5.307, respectively. Our results could provide data and technological support for soil water and nutrient monitoring, quality improvement, and graphics creating in similar area with medium to low yield fields.

Artificial intelligence-based framework for precise prediction of asphaltene particle aggregation kinetics in petroleum recovery

The precipitation and deposition of asphaltene on solid surfaces present a significant challenge throughout all stages of petroleum recovery, from hydrocarbon reservoirs in porous media to wellbore and transfer pipelines. A comprehensive understanding of asphaltene aggregation phenomena is crucial for controlling deposition issues. In addition to experimental studies, accurate prediction of asphaltene aggregation kinetics, which has received less attention in previous research, is essential. This study proposes an artificial intelligence-based framework for precisely predicting asphaltene particle aggregation kinetics. Different techniques were utilized to predict the asphaltene aggregate diameter as a function of pressure, temperature, oil specific gravity, and oil asphaltene content. These methods included the adaptive neuro-fuzzy interference system (ANFIS), radial basis function (RBF) neural network optimized with the Grey Wolf Optimizer (GWO) algorithm, extreme learning machine (ELM), and multi-layer perceptron (MLP) coupled with Bayesian Regularization (BR), Levenberg–Marquardt (LM), and Scaled Conjugate Gradient (SCG) algorithms. The models were constructed using a series of published data. The results indicate the excellent correlation between predicted and experimental values using various models. However, the GWO-RBF modeling strategy demonstrated the highest accuracy among the developed models, with a determination coefficient, average absolute relative deviation percent, and root mean square error (RMSE) of 0.9993, 1.1326%, and 0.0537, respectively, for the total data.

Accurate ECG monitoring by Gaussian feature streaming

Wearable cardiac monitors can usefully contribute to early detection of potential cardiovascular pathologies. However ECG trace data streaming over wireless links creates some significant challenges, due to the amount of data to be transmitted. We employ a signal analysis approach based on a Gaussian dictionary to model ECG traces in a compressed way. The algorithm operates on fixed-length segments, and achieves effective compression for wireless data transmission, associating just 6 bytes to each Gaussian feature. At the same time it enables accurate reconstruction of ECG traces from the reduced data set. We tested our method on a set of 46 ECG recordings taken from the Physionet MIT-BIH Arrhythmia Database, obtaining 90% data compression rates, while percent relative deviation of reconstructed traces is always below 5%.

Monitoring of simultaneous saccharification and fermentation of ethanol by multi-source data deep fusion strategy based on near-infrared spectra and electronic nose signals

Fuel ethanol represents a future energy trajectory, and the simultaneous saccharification and fermentation (SSF) technique emerges as the principal approach for ethanol production. This scholarly inquiry offers an innovative means to monitor the SSF process for ethanol meticulously. Employing a profound fusion strategy that effectively amalgamates diverse data sources. The convolutional neural network and recurrent neural network (RNN) architectures are thoughtfully crafted and designed to enable autonomous feature self-learning from near-infrared spectra and electronic nose data. These intricately devised networks further implement data fusion strategies at the granular level of features. Ultimately, a deep fusion correction model was devised and rigorously validated using two distinct data sources, namely near-infrared spectroscopy and electronic nose data. The obtained results demonstrate a discernible improvement in the overall predictive accuracy of the model when employing the fusion feature strategy, surpassing the model constructed solely on a single technical data source. Regarding the monitoring of ethanol content, the optimal RNN fusion model exhibited remarkable performance metrics, with a root mean square error of prediction (RMSEP) value of 3.2265, a coefficient of determination (R2) value of 0.9880, and a relative percent deviation (RPD) value of 9.2662. In terms of monitoring glucose content, the optimal RNN fusion model also demonstrated commendable performance, with the following respective parameters: RMSEP was 3.2770, R2 was 0.9840, and RPD was 8.0085. The overall results indicate that the multi-sensor data fusion strategy not only improves the performance of the model but also provides valuable insights into the fermentation process.

Predicting sulfanilamide solubility in mixed solvents: A comparative analysis of computational models

The Jouyban-Acree model is the most common in the solubility prediction area. This work focused on providing the various mathematical models derived from the Jouyban-Acree equation for the solubility prediction of sulfanilamide in nine binary solvent mixtures in the 278.15 to 318.15 K temperature range. 24 various computational models are reported in this work, which are derived from the Jouyban-Acree equation and include the terms Abraham solute, solvent, Hansen solubility parameters, QSPR, and Yalkowsky models with the Van't Hoff and Apelblat parameters. This study reveals the reliability of the predicted solubility values from these 24 different computational models compared with one another's equations. By calculating the %ARD, it was validated that any variation to the Jouyban-Acree equation's parameters, including those that affect the solute, solvent, and Hansen solubility properties, in addition to the Van't Hoff, Apelblat parameters, and Yalkowsky model, made any difference in the solubility values as compared to experimentally obtained solubility data that had previously been published. Using mono-solvent solubility data to calculate binary solubility with the Yalkowsky model can be a useful and efficient approach, and it could be especially important in situations where experimental binary solubility data is limited or unavailable. However, the Yalkowsky model showed a low overall percentage relative deviation of 60.930 % compared to other computed models. In the binary solvent systems, the Yalkowsky model had the least %ARD in methanol (w) + ethanol (1-w) (3.77 %), followed by acetone (w) + methanol (1-w) (9.34 %) and acetone (w) + ethanol (1-w) (23.57 %). The Modified Yalkowsky-Jouyban-Acree Model, in combination with the Abraham Solute Parameter Model, demonstrated the lowest %ARD of 3.81 % in the methanol (w) + ethanol (1-w) binary mixture. Similarly, in most combined versions of the Jouyban-Acree models incorporating various Apelblat and Van't Hoff parameters, the lowest %ARD observed was 10.16 % in the methanol (w) + ethanol (1-w) binary mixture. The Yalkowsky model also showed a lower average percentage deviation than other models in acetone, methanol, and ethanol as the first solvent, with values of 50.535 %, 58.943 %, and 84.7 %, respectively. The Yalkowsky model provided a good fit to the experimental data, with regression coefficients of 0.87895, 0.96911, and 0.98164 for acetone, ethanol, and methanol as the first solvents in binary solvent systems.

Detection of anthocyanin content in fresh Zijuan tea leaves based on hyperspectral imaging

Anthocyanins are characteristic substances that determine the leaf color and sensory quality of Zijuan tea. The qualitative determination of anthocyanin content in fresh Zijuan tea leaves by artificial vision may lead to the uneven quality of tea products. Hyperspectral images at 400–956 nm were obtained. K-nearest neighbor (KNN) and support vector machine (SVM) models were used to identify the tenderness grade, and partial least squares regression (PLSR) and support vector regression (SVR) models were established based on principal component analysis for prediction. In short, the classification accuracy of the SVM model was better than 90%; variable combination population analysis (VCPA) and variables combination population analysis combined with iterative retained information variable (VCPA-IRIV) can effectively simplify the model and the prediction accuracy is over than 0.92. The best predictive models of total anthocyanins, Cya-3,5-O-diglucoside, Cya-3-O-glucoside, and petunidin were VCPA + SVR, VCPA-IRIV + SVR, VCPA-IRIV + PLSR, and VCPA + PLSR, and the relative percent deviation were 3.233, 2.868, 3.529 and 3.298, respectively. The total anthocyanins were visualized by the spatial distribution of anthocyanins in samples with different tenderness. This study provided a rapid nondestructive method of fresh Zijuan tea leaf tenderness grade and quality components to control the quality of fresh leaf picking of tea with specific leaf color.

Estimation of leaf nitrogen content in winter wheat based on continuum removal and discrete wavelet transform

ABSTRACT Accurate and rapid estimation of leaf nitrogen content (LNC) in winter wheat using hyperspectral techniques is important for growth monitoring and accurate fertilization. Based on field experiments conducted over four years at three ecological sites with four different nitrogen (N) application treatments and four different N-efficient wheat varieties in Henan Province, the canopy spectra and LNC of winter wheat were obtained simultaneously in the main growth stages. The original spectrum was subjected to continuum removal (CR), the correlation between LNC and various vegetation indices was systematically analysed, and the optimal vegetation index estimation model for LNC was constructed. Simultaneously, discrete wavelet transform (DWT) was used to further compress and extract the CR spectrum. The model was combined with partial least squares regression (PLSR) and K-nearest neighbour (KNN) algorithms to estimate LNC in winter wheat. The results showed that the spectrum treated with CR was significantly improved in its correlation with LNC and that the model established based on normalized vegetation index NDVI (CR728, CR977) combined with the CR spectrum was better compared to existing vegetation indices. The calibration and validation coefficients of determination (R2) and root mean square error (RMSE) were 0.816 and 0.799, and 0.352% and 0.342%, respectively. DWT was used to transform the CR spectrum, and the results showed that a combination of the CR spectrum and a sym8 wavelet function with PLSR based on the approximation coefficients at decomposition level 2 predicted LNC most accurately. The coefficient of determination RC 2, root mean square error RMSEC, and relative percent deviation (RPDC) of the calibration set were 0.884, 0.279%, and 2.932, respectively, and RV 2, RMSEV, and RPDV of the validation set were 0.855, 0.291%, and 2.619, respectively, indicating that the model had good stability and predictive ability. Combination of CR and DWT improved the modelling accuracy of wheat LNC and showed better prediction results for multi-year and multi-point samples. The results of the study can provide a basis and reference for rapid monitoring of LNC in winter wheat.

Ginsenoside Rg2 content prediction in Panax ginseng based on the fusion of hyperspectral wavelengths combined with chemometric analysis

The content of ginsenosides plays a crucial role in determining the quality of Panax ginseng C. A. Meyer. In order to clarify the potential applicability of hyperspectral imaging (HSI) for fast detecting the quality of ginseng, this study investigated the use of HSI combined with chemometric models to predict the ginsenoside Rg2 content. The results indicated that the prediction efficiency can be improved through complete wavelength fusion of different shots and the effective wavelength fusion obtained by different selection methods. Notably, the integrated utilization of the partial least squares regression (PLSR) algorithm and the fusion of effective wavelengths exhibited the best results in Rg2 content prediction, with the maximum coefficient of determination (R2) and relative percent deviation (RPD) values of 0.939 and 3.35, respectively, as well as the lowest root mean squared error (RMSE) value of 24.2 μg/g, indicating excellent model performance. This study provides valuable insights for the development and application of portable HSI equipment for rapid and non-destructive testing of Panax ginseng quality.

An Estimation of Distribution Algorithm for Permutation Flow-Shop Scheduling Problem

Estimation of distribution algorithms (EDAs) is a subset of evolutionary algorithms widely used in various optimization problems, known for their favorable results. Each generation of EDAs builds a probabilistic model to represent the most promising individuals, and the next generation is created by sampling from this model. The primary challenge in designing such algorithms lies in effectively constructing the probabilistic model. The mutual exclusivity constraint imposes an additional challenge for EDAs to approach permutation-based problems. In this study, we propose a new EDA called Position-Guided Sampling Estimation of Distribution Algorithm (PGS-EDA) specifically designed for permutation-based problems. Unlike conventional approaches, our algorithm focuses on the positions rather than the elements during the sampling phase. We evaluate the performance of our algorithm on the Permutation Flow-shop Scheduling Problem (PFSP). The experiments conducted on various sizes of Taillard instances provide evidence of the effectiveness of our algorithm in addressing the PFSP, particularly for small and medium-sized problems. The comparison results with other EDAs designed to handle permutation problems demonstrate that our PSG-EDA algorithm consistently achieves the lowest Average Relative Percentage Deviation (ARPD) values in 19 out of the 30 instances of sizes 20 and 50 used in the study. These findings validate the superior performance of our algorithm in terms of minimizing the makespan criterion of the PFSP.

Prediction performance and reliability evaluation of three ginsenosides in Panax ginseng using hyperspectral imaging combined with a novel ensemble chemometric model

Panax ginseng C. A. Meyer (PG) is a health-promoting food, and its ginsenosides (Rb1, Rg1, Re) content, as the quality indicator, is affected by the planting modes (garden or forest ginsengs) and years. Effective prediction of this content remains to be investigated. In this study, hyperspectral (HSI) combined with ensemble model (CGRU-GPR) including the convolutional neural network (CNN), gate recurrent unit (GRU), and Gaussian process regression (GPR) realized a comprehensive evaluation of the prediction performance and predictive uncertainty. With effective wavelengths, the proposed CGRU-GPR model improved operation efficiency and obtained satisfactory prediction results with relative percent deviation (RPD) values all higher than 2.70 in three ginsenosides. Meanwhile, the interval prediction with a high prediction interval coverage probability (PICP) of 0.97 – 1.0 and a low mean width percentage (MWP) of 0.7 – 1.66 indicated a low prediction uncertainty. This study provides a rapid and reliable method for predicting ginsenosides contents in PG.

Quantitative analysis of aflatoxin B1 of peanut by optimized support vector machine models based on near-infrared spectral features

This study designs a chemometric framework for quantitatively evaluating aflatoxin B1 (AFB1) in peanuts based on near-infrared (NIR) spectroscopy technique. The NIR spectra of peanut samples exhibiting diverse fungal contamination levels were acquired using a portable NIR spectrometer. Subsequently, appropriate pre-processing techniques were employed for data refinement. To streamline the analysis, the iterative variable subset optimization (IVSO) technique was employed to conduct an initial screening of the pre-processed NIR spectra, eliminating numerous irrelevant variables. Building upon this screening process, the beluga whale optimization (BWO) algorithm was utilized to optimize the selected feature variables further. Subsequently, support vector machine (SVM) models were developed using the refined near-infrared spectral features to test AFB1 in peanuts quantitatively. The results indicate that the SVM model significantly improves detection performance and generalization proficiency, particularly after secondary optimization using BWO-IVSO. Among the different models considered, the SVM model established after BWO-IVSO optimization exhibited the most extraordinary level of generalization, with a root mean square error of prediction of 24.6322 μg∙kg−1, a correlation coefficient of 0.9761, and a relative percent deviation of 4.6999. Overall, this investigation highlights the effectiveness of the proposed NIR spectroscopy model based on BWO-IVSO-SVM for quantitatively analyzing AFB1 in peanuts. The study contributes valuable technical and methodological insights that can serve as a reference for rapidly determining mycotoxins in cereal crops.

New Ant Colony Algorithm for Solving Partial Job Shop Scheduling Problem

Scheduling problems are one of the most researched topics in the field of operational research. Scheduling problem models have evolved and branched because of the wide range of products, standards, and customer requirements. Recently, the partial job shop scheduling problem, which is a general model of shop scheduling problems, has become a new scheduling problem. Operations in this model are partially ordered, and the order varies for each job. Several problems studied independently in the literature, such as the group shop, mixed shop, job shop, and open shop scheduling problems, are considered special cases of the partial shop scheduling model. Because ant algorithms are known in the literature as effective tools for solving combinatorial optimization problems, this study proposed an ant colony (AC) algorithm for solving partial shop problems with an objective function to minimize makespan. The AC method was examined and evaluated on the renowned “Taillerd” benchmark instances. It was then compared with the hybrid scatter search (HSS) and iterated tabu search (ITS) methods. The AC algorithm’s average deviation for 80 instances ranged between 0% and 1.78%. The AC algorithm outperforms the HSS and ITS methods, according to the computational findings; where the average percentage relative deviation for AC is 0.66%, compared with 0.99% for ITS and 10.14% for HSS.

Quantitative analysis of residues of chlorpyrifos in corn oil based on Fourier transform near-infrared spectroscopy and deep transfer learning

This study introduces a novel deep transfer learning (DTL) approach based on convolutional neural networks (CNN) and Fourier transform near-infrared (FT-NIR) spectroscopy to enhance the accuracy of predicting the residual levels of chlorpyrifos in corn oil. The method proposed involves creating a 1D-CNN model using existing data and utilizing DTL to enhance the performance of a new model by transferring the parameters learned from the trained model. The research findings demonstrate that compared to the CNN model, the proposed TL method achieves superior predictive accuracy while utilizing a smaller amount of FT-NIR spectral data, thus reducing the reliance on labeled FT-NIR spectral data for model training. Specifically, the coefficient of determination (RP2) reaches 0.9754, and the relative percent deviation (RPD) is 6.4575. This study confirms that the developed DTL method based on CNN and FT-NIR provides an efficient and precise approach to detecting food safety issues. In addition, this method is not only applicable for pesticide residue detection in edible oils based on near-infrared spectroscopy but can also be used for the chemometric analysis of FT-NIR spectral data in other fields.

An artificial immune differential evolution algorithm for scheduling a distributed heterogeneous flexible flowshop

This paper studies a distributed heterogeneous flexible flowshop problem (DHFFP) with sequence-dependent setup and transport times, where each job has a release time and each production stage has multiple unrelated parallel machines. An integer linear programming (ILP) model and a new artificial immune differential evolution (AIDE) algorithm are proposed aiming to minimize the makespan and total tardiness simultaneously. Firstly, the AIDE employs a two-dimensional vector encoding scheme including the information of job permutation and factory allocation for solution representation. In addition, a dynamic decoding scheme is designed to construct a feasible schedule. Secondly, three distributed Nawaz–Enscore–Ham (NEH) based constructive heuristics are presented to provide the initial antibody population. Thirdly, a discrete differential evolution algorithm is introduced to mutate the cloned antibodies. Further, clonal suppression is applied by eliminating the antibodies with lower stimulation values. Simulated annealing (SA) based local search is incorporated with four problem-specific neighborhood structures to enhance the algorithm. Finally, the optimal values of the algorithmic parameters are determined by the orthogonal test. Some numerical experiments of the ILP model on small-scale instances are conducted to show the effectiveness of the proposed AIDE algorithm. The AIDE algorithm is also compared with several existing algorithms for different scale instances. The results demonstrate that the AIDE algorithm generates average relative percentage deviation of 12.51% and 7.99% respectively for small & medium-scale instances and large-scale instances, which is the best-performing among all algorithms.

Development of advanced model for understanding the behavior of drug solubility in green solvents: Machine learning modeling for small-molecule API solubility prediction

Determination of small-molecule API (Active Pharmaceutical Ingredient) solubility in solvents is of great importance for drug development in pharmaceutical industry. This study uses machine learning algorithms to predict the solubility of phenytoin drug and density of the solvent at different pressure and temperature. In fact, the solubility of drug (y) and the density of supercritical CO2 (Sc-CO2) were investigated as functions of temperature (T) and pressure (P). Three regression models, namely Gaussian Process Regression (GPR), Gamma Regression (GR), and K-nearest neighbor (KNN) were employed to predict the output variables. To optimize the performance of these models, the Directional Bat Algorithm (dBA) was utilized for hyper-parameter tuning. The outputs demonstrated the accuracy of the developed models in predicting the Sc-CO2 density and solubility of phenytoin. Among the models, GPR exhibited the highest accuracy for both outputs, achieving an R2 value of 0.99 for the solvent density and 0.999 for the solubility. The root mean square error (RMSE) for Sc-CO2 density was approximately 18.37, with an average absolute relative deviation percentage (AARD%) of 4.07% and a maximum error of 37.42. For solubility, the RMSE was approximately 0.087, with an AARD% of 2.29% and a maximum error of 0.150.

Hyperspectral prediction of pigment content in tomato leaves based on logistic-optimized sparrow search algorithm and back propagation neural network

Leaf pigment content can reflect the nutrient elements content of the cultivation medium indirectly. To rapidly and accurately predict the pigment content of tomato leaves, chlorophyll a, chlorophyll b, chlorophyll and carotenoid were extracted from leaves of tomato seedlings cultured at different nitrogen concentrations. The visible/near-infrared(VIS/NIR) hyperspectral imaging (HSI) non-destructive measurement technology, 430-900 nm and 950-1650 nm, with total variables of 794, was used to obtain the reflection spectra of leaves. An improved strategy of the sparrow search algorithm (SSA) based on Logistic chaotic mapping was proposed and optimized the back propagation (BP) neural network to predict the pigment content of leaves. Different pretreatment methods were used to effectively improve the prediction accuracy of the model. The results showed that when the nitrogen concentration in the nutrient solution was 302.84 mg·L-1, the pigment content of leaves reached the maximum. Meanwhile, the inhibition effect of high concentration was much stronger than that of low concentration. To address the problem that the SSA is prone to get in premature convergence due to the reduction of population diversity at the end of the iteration, the initialization of the SSA population by Logistic chaotic mapping improves the initial solution quality, convergence speed and search capacity. The root mean squared error (RMSE), coefficient of determination (R2) and relative percent deviation (RPD) of chlorophyll a were 0.77, 0.77 and 2.08, respectively. The RMSE, R2 and RPD of chlorophyll b were 0.30, 0.66 and 1.71, respectively. The RMSE, R2 and RPD of chlorophyll were 0.88, 0.81 and 2.28, respectively. The RMSE, R2 and RPD of carotenoid were 0.14, 0.75 and 2.00, respectively. The HSI technology combined with machine learning algorithms can achieve rapid and accurate prediction of crop physiological information, providing data support for the precise management of fertilization in facility agriculture, which is conducive to improving the quality and output of tomatoes.

Improved multivariate modeling for soil organic matter content estimation using hyperspectral indexes and characteristic bands.

Soil organic matter (SOM) is a key index of soil fertility. Calculating spectral index and screening characteristic band reduce redundancy information of hyperspectral data, and improve the accuracy of SOM prediction. This study aimed to compare the improvement of model accuracy by spectral index and characteristic band. This study collected 178 samples of topsoil (0-20 cm) in the central plain of Jiangsu, East China. Firstly, visible and near-infrared (VNIR, 350-2500 nm) reflectance spectra were measured using ASD FieldSpec 4 Std-Res spectral radiometer in the laboratory, and inverse-log reflectance (LR), continuum removal (CR), first-order derivative reflectance (FDR) were applied to transform the original reflectance (R). Secondly, optimal spectral indexes (including deviation of arch, difference index, ratio index, and normalized difference index) were calculated from each type of VNIR spectra. Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. Meanwhile, SOM prediction models were established using characteristic wavelengths, denoted here as CARS-based models. Finally, this research compared and assessed accuracy of SI-based models and CARS-based models, and selected optimal model. Results showed: (1) The correlation between optimal spectral indexes and SOM was enhanced, with absolute value of correlation coefficient between 0.66 and 0.83. The SI-based models predicted SOM content accurately, with the coefficient of determination (R2) and root mean square error (RMSE) values ranging from 0.80 to 0.87, 2.40 g/kg to 2.88 g/kg in validation sets, and relative percent deviation (RPD) value between 2.14 and 2.52. (2) The accuracy of CARS-based models differed with models and spectral transformations. For all spectral transformations, PLSR and SVR combined with CARS displayed the best prediction (R2 and RMSE values ranged from 0.87 to 0.92, 1.91 g/kg to 2.56 g/kg in validation sets, and RPD value ranged from 2.41 to 3.23). For FDR and CR spectra, DNN and RF models achieved more accuracy (R2 and RMSE values ranged from 0.69 to 0.91, 1.90 g/kg to 3.57 g/kg in validation sets, and RPD value ranged from 1.73 to 3.25) than LR and R spectra (R2 and RMSE values from 0.20 to 0.35, 5.08 g/kg to 6.44 g/kg in validation sets, and RPD value ranged from 0.96 to 1.21). (3) Overall, the accuracy of SI-based models was slightly lower than that of CARS-based models. But spectral index had a good adaptability to the models, and each SI-based model displayed the similar accuracy. For different spectra, the accuracy of CARS-based model differed from modeling methods. (4) The optimal CARS-based model was model CARS-CR-SVR (R2 and RMSE: 0.92 and 1.91 g/kg in validation set, RPD: 3.23). The optimal SI-based model was model SI3-SVR (R2 and RMSE: 0.87 and 2.40 g/kg in validation set, RPD: 2.57) and model SI-SVR (R2 and RMSE: 0.84 and 2.63 g/kg in validation set, RPD: 2.35).

Soil carbon content prediction using multi-source data feature fusion of deep learning based on spectral and hyperspectral images

Visible near-infrared reflectance spectroscopy (VNIR) and hyperspectral images (HSI) have their respective advantages in soil carbon content prediction, and the effective fusion of VNIR and HSI is of great significance for improving the prediction accuracy. But the contribution difference analysis of multiple features in the multi-source data is inadequate, and there is a lack of in-depth research on the contribution difference analysis of artificial feature and deep learning feature. In order to solve the problem, soil carbon content prediction methods based on VNIR and HSI multi-source data feature fusion are proposed. The multi-source data fusion network under the attention mechanism and the multi-source data fusion network with artificial feature are designed. For the multi-source data fusion network based on the attention mechanism, the information are fused through the attention mechanism according to the contribution difference of each feature. For the other network, artificial feature are introduced to fuse multi-source data. The results show that multi-source data fusion network based on the attention mechanism can improve the prediction accuracy of soil carbon content, and multi-source data fusion network combined with artificial feature has better prediction effect. Compared with two single-source data from the VNIR and HSI, the relative percent deviation of Neilu, Aoshan Bay and Jiaozhou Bay based on multi-source data fusion network combined with artificial feature are increased by 56.81% and 149.18%, 24.28% and 43.96%, 31.16% and 28.73% respectively. This study can effectively solve the problem of the deep fusion of multiple features in the soil carbon content prediction by VNIR and HSI, so as to improve the accuracy and stability of soil carbon content prediction, promote the application and development of soil carbon content prediction in spectral and hyperspectral image, and provide technical support for the study of carbon cycle and the carbon sink.

Heuristic approaches to address vehicle routing problem in the Iot-based waste management system

Nowadays, population growth and urban development lead to having an efficient waste management system (WMS) based on recent advances and trends. Alongside all functions and procedures in these systems, the waste collection plays a significant role. This study proposes a two-echelon WMS to minimize operational costs and environmental impact by utilizing the industry 4.0 concept. Both models utilize modern traceability Internet of Thing-based devices to compare real-time information of waste level in bins and separation centers with the threshold waste level (TWL) parameter. The first model optimizes the operational cost and CO2 emission of collecting waste from bins to the separation center by considering the time windows. A capacitated vehicle routing problem is designed as a later model-based to minimize the cost of waste transferring to recycling centers. In addition, to find the optimal solution, recent meta-heuristic algorithms are employed, and several novel heuristics based on the problem's specifications are developed. Furthermore, the developed heuristics methods are utilized to generate the initial feasible solutions in meta-heuristics and compared with random ones. The performance of the proposed algorithms is probed, and Best Worst Method (BWM) is applied to rank the algorithms based on relative percentage deviation, relative deviation index and hitting time.

Solving a Cubic Cell Formation Problem with Quality Index Using a Hybrid Meta-Heuristic Approach

Although most previous studies on cell formation have involved the assignment of parts and machines to cells, in recent years the assignment of workers has also been considered and the studies have taken into account the human factor. An important step for the successful implementation of a Cellular Manufacturing System is to decide appropriate groups of parts, machines, and workers and then assign them to cells. Consideration of the skills of workers and machines in processing parts has enhanced cell performance. In this study, the problem of a cubic cell formation that takes into account the three-dimensional part-machine-worker matrix is addressed, and the minimization of the exceptional element and void as well as the maximization of the part quality index is aimed. The mathematical model used in this study was coded in the GAMS 24.2.1 software. A hybrid GA-SA approach was also proposed for the solution of large instances. The relative Percentage Deviation performance index was utilized to evaluate the performance of the algorithm. According to the results, the hybrid technique developed, considering technical cell performance criteria together with worker skills, shows promising results from the standpoint of the considered objective and the computational time.