Unmixing urban hyperspectral imagery using probability distributions to represent endmember variability

Prediction of soil organic carbon content by diffuse reflectance spectroscopy using a local partial least square regression approach

High-precision transient fuel consumption model based on support vector regression

Object detection and counting in video surveillance is a crucial task with various applications, yet it faces significant challenges due to dynamic environmental conditions such as varying illumination, occlusions, and noise. This research evaluates and compares the performance of two prominent background subtraction techniques: Gaussian Mixture Model (GMM) and Fuzzy Logic, for moving object segmentation and counting. The methodology involves image preprocessing (grayscale conversion, Gaussian blur, normalization), background model generation using the median of initial frames, object segmentation with both GMM and Fuzzy Logic enhanced by Region of Interest (ROI) and morphological operations, and object tracking using a simple Centroid Tracker. Performance was evaluated using segmentation metrics (Precision, Recall, F1-score, Percentage of Wrong Classifications (PWC)) and counting accuracy metrics (Mean Absolute Error (MAE), Accuracy). Results indicate that GMM achieved a slightly better F1-score (0.23 vs 0.18) for segmentation, while Fuzzy Logic demonstrated marginally higher Precision (0.37 vs 0.33). For object counting, both methods yielded an identical average MAE of 0.94, with Fuzzy Logic showing a slightly higher average accuracy (9.88% vs 9.41%). The study highlights that both GMM and Fuzzy Logic are viable for moving object detection and counting, each with distinct strengths and weaknesses, but performance remains sensitive to dynamic scene conditions. The dataset utilized, CDnet's "night videos" category, specifically the "busyBoulvard" sequence, presented unique challenges due to low light and dense traffic, which were central to the evaluation.

Global warming has constituted a major global problem. Carbon dioxide emissions from the burning of fossil fuels are the main cause of global warming. Therefore, carbon dioxide emission forecasting has attracted widespread attention. Aiming at the problem of carbon dioxide emissions forecasting, this paper proposes a new hybrid forecasting model of carbon dioxide emissions, which combines the marine predator algorithm (MPA) and multi-kernel support vector regression. For further strengthening the prediction accuracy, a novel variant of MPA is proposed, called EGMPA, which introduces the elite opposition-based learning strategy and the golden sine algorithm into MPA. Algorithm test results show that EGMPA can effectively improve the convergence speed and optimization accuracy. The carbon dioxide emission data of China from 1965 to 2020 are taken as the research objects. Root-mean-square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) are used to evaluate the performance of the proposed model. The proposed multi-kernel support vector regression model is used to forecast China’s carbon dioxide emissions during the “14th Five-Year Plan” period. The results show that the proposed model has RMSE of 37.43 Mt, MAE of 30.63 Mt, and MAPE of 0.32%, which significantly improves the prediction accuracy and can accurately and effectively predict China’s carbon dioxide emissions. During the “14th Five-Year Plan” period, China’s carbon dioxide emissions will continue to show an increasing trend, but the growth rate will slow down significantly.

Salient object detection in a real-time environment demands high accuracy with less computation time. It is a changeling task to investigate a saliency model which improves saliency detection accuracy as well as reduces computation time. In this paper, we propose a hybrid model that improves detection accuracy with low computational time. The input image is simplified and clustered at multiple scales using SLIC and K-means clustering algorithms respectively. Gaussian Mixture Model (GMM) is developed on various color components of the digital image at multiple scales. The parameters of GMM are learnt using Expectation Maximization (EM) algorithm. The spatial variance of each color component is determined using GMM parameters and hence object position is estimated. Further, spatial variance of color components and object position is exploited to compute saliency map at a scale level. Afterwards, all the saliency maps generated across various scales are linearly combined to produce the final saliency map. The performance of the proposed model is compared in terms of Precision, Recall, F-Measure, Area under the Curve (AUC), Receiver Operating Characteristics (ROC) and Mean Absolute Error (MAE). Extensive experiments on six publicly available datasets viz. MSRA10K, DUT-OMRON, ECSSD, PASCAL-S, SED2, and THUR15K show that the proposed model outperforms or comparable against 11 state-of-the-art methods of the last decade. The key features of the proposed method are object completeness and efficiency in terms of computational time.

The purpose of this study is to predict the decade rainfall in Semarang City using two main methods, namely Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) and Long Short Term Memory (LSTM). The methodology of this study begins with data pre-processing, which includes data deletion analysis using dropna and data normalization using Min-Max Scaling to reduce scale the to between 0 and 1. The dataset is then divided into 80% training data and 20% test data. The validity of the data (X_test, Y_test) using the best 56-epoch data validation (val_loss) is better than the validity of the training data (loss). On the other hand, SARIMAX uses the (2,1,2), (2,1,2,36) model, and its validation techniques include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2). Specifically, the RMSE of the LSTM model is 19.6, and its RMSE of the SARIMAX is 31.05. The MAE of LSTM is 15.0, SARIMAX is 24.5, and the R2 of LSTM is 0.814, and SARIMAX is 0.52. Lower RMSE and MAE values indicate lower prediction errors, but a higher R2 value of 1 indicates that LSTM can explain 81% of the actual data variation, which is better than SARIMAX, which is only about 52%. The main finding of this study is that the LSTM model performs better when recommending rainfall datasets.

Product ion spectra obtained with liquid chromatography-electrospray ionization tandem mass spectrometry (LC-ESI/MS/MS) were applied to the identification of seized drug samples from atmospheric pressure matrix-assisted laser desorption/ionization product ion spectra (AP-MALDI-MS/MS spectra). Data acquisition was performed in the information-dependent acquisition (IDA) mode, and the substance identification was based on a spectral library previously created with LC-ESI/MS/MS using protonated molecules as precursor ions. A total of 39 seized drug samples were analyzed with both AP-MALDI and LC-ESI techniques using the same triple-quadrupole instrument (AB Sciex 4000QTRAP). The study shows that ESI-MS/MS spectra can be directly utilized in AP-MALDI-MS/MS measurements as the average fit and purity score percentages with AP-MALDI were 90% and 85%, respectively, being similar to or even better than those obtained with the reference LC/ESI-MS/MS method. This fact enables the possibility to use large ESI spectral libraries, not only to ESI analyses but also to analyses with other ionization techniques which produce protonated molecules as the base peak. The data obtained shows that spectral library search works also for analytical techniques which produce multi-component mass spectra, such as AP-MALDI, unless isobaric compounds are encountered. The spectral library search was successfully applied to rapid identification of confiscated drugs by AP-MALDI-IDA-MS/MS.

A method to estimate the water storage of on-farm reservoirs by detecting slope gradients based on multi-spectral drone data

Building height is a critical variable in urban studies, and the automated acquisition of the precise building height is essential for intelligent construction, safety, and the sustainable development of cities. The building height is often approximated by the building’s highest point. However, the calculation method of the building height of the various roof types differs according to building codes, making it challenging to accurately calculate the height of buildings with complex roof structures or multiple upper appendages. Consequently, this paper utilizes point clouds to propose an automated method for calculating building heights conforming to design codes. The model considers roof types and allows for fast, automated, and highly accurate building height estimation. First, roofs are extracted from the point cloud by combining normal vector density clustering with a region-growing algorithm. Second, combined with variational Bayes, a Gaussian mixture model is employed to segment the roof surfaces. Finally, roofs are classified based on slope characteristics, achieving the automatic acquisition of building heights for various roof types over large areas. Experiments were conducted on Vaihingen and STPLS3D datasets. In the Vaihingen area, the maximum error, root-mean-square-error (RMSE), and mean absolute error (MAE) of the measured heights are 1.92 cm, 1.18 cm, and 1.13 cm, respectively. In the STPLS3D area, these values are 1.79 cm, 0.82 cm, and 0.68 cm, respectively. The results demonstrate that the proposed method is reliable and effective, which offers valuable data for the development, construction, and planning of three-dimensional (3D) cities.

In this paper, Prediction of groundwater level is made from different states. In order to describe this information for the states and created seasonal models to depict groundwater activity, The developed models in this manner may be expanded for use by the individual remote sensing techniques created by the Division for Self-Organizing Cognitive Computing (CSOIS). When it came to minimising, Support vector regression consistently beat other techniques both root mean square error and mean absolute error. Additionally, Models that could be constructed using only local geographic information seemed to have more error than those that could be established with taking a global feature from a Gaussian Mixture Model.

The identification and characterisation of V genes poses a significant challenge due to the substantial number of alignments generated by diverse sequencing systems. This study proposes a method for the unification and reduction of the search space, with the objective of optimising the identification of V genes. The method integrates preprocessing, normalisation, and clustering using Gaussian Mixture Models. This approach facilitates data consolidation and reduces redundancy, thereby enhancing the efficiency and accuracy of the subsequent analysis. The elbow method was employed to determine the optimal number of groups, achieving a 98% reduction in the search space. The findings were validated through the use of metrics such as mean absolute error, mean squared error, and root mean squared error, thereby confirming the effectiveness of the method in improving the precision of gene identification.

In recent years, the increasing availability of spectral libraries has opened a new path toward solving the hyperspectral unmixing problem in a semi-supervised fashion. The spectrally pure constituent materials (called endmembers) can be derived from a (potentially very large) spectral library and used for unmixing purposes. The advantage of this approach is that the results of the unmixing process do not depend on the availability of pure pixels in the original hyperspectral data nor on the ability of an endmember extraction algorithm to identify such endmembers. However, resulting from the fact that spectral libraries are usually very large, this approach generally results in a sparse solution. In this paper, we investigate the sensitivity of sparse unmixing techniques to certain characteristics of real and synthetic spectral libraries, including parameters such as mutual coherence and spectral similarity between the signatures contained in the library. Our main goal is to illustrate, via detailed experimental assessment, the potential of using spectral libraries to solve the spectral unmixing problem.

A wavelet-based Markov random field segmentation model in segmenting microarray experiments

Designing a battery management system requires knowing the battery's remaining useful life (RUL). The Deep Learning Neural Network (DLNN) algorithm was optimized in this study utilizing evolutionary algorithms to forecast the RUL batteries. Using a Genetic Algorithm (GA), the most crucial features from the raw dataset were identified. After that, a GADLNN hybrid model was created to choose the DLNN model's ideal network algorithm, hidden neuron activation function, hidden layer count, and neuron count in each hidden layer. Specifically, NASA provided a dataset related to lithium-ion battery cycle life. For the model development, data validation, and testing phases, the dataset was split into a training set, validation set, and testing set. Several quality assessment criteria were employed to measure the effectiveness of the machine learning (ML) algorithms, such as the Coefficient of Determination (R2), Index of Agreement (IA), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The hybrid GA-DLNN model demonstrated the capacity to identify the most advantageous set of parameters for the prediction procedure. The outcomes demonstrated that, in comparison to results obtained using all input variables, the performance of the hybrid model employing only the most crucial features gave the maximum accuracy. Using 11-input GA-DLNN: R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.985,MAE=3.806, RMSE =5.596, IA=0.996. Using 21-input GA-DLNN: R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.987, MAE=3.314, RMSE =5.273, IA=0.997.

Validation of the micro-EROD assay with H4IIE cells for assessing sediment contamination with dioxin-like chemicals