Search Results (26)

Real-time ash content control in dense medium coal separation is challenged by time lags between detection and density adjustment, along with nonlinear/noisy signals. This study proposes a hybrid model for clean coal ash content in dense medium separation by integrating empirical mode decomposition, long short-term memory networks, and sparrow search algorithm optimization. A key innovation lies in removing noise-containing intrinsic mode functions (IMFs) via EMD to ensure clean signal input to the LSTM model. Utilizing production data from a Shanxi coal plant, EMD decomposes ash content time series into intrinsic mode functions (IMFs) and residuals. High-frequency noise-containing IMFs are selectively removed, while LSTM predicts retained components. SSA optimizes LSTM parameters (learning rate, hidden layers, epochs) to minimize prediction errors. Results demonstrate the EMD-IMF1-LSTM-SSA model achieves superior accuracy (RMSE: 0.0099, MAE: 0.0052, MAPE: 0.047%) and trend consistency (NSD: 12), outperforming baseline models. The study also proposes the novel “Vector Value of the Radial Difference (VVRD)” metric, which effectively quantifies prediction trend accuracy. By resolving time-lag issues and mitigating noise interference, the model enables precise ash content prediction 16 min ahead, supporting automated density control, reduced energy waste, and eco-friendly coal processing. This research provides practical tools and new metrics for intelligent coal separation in the context of green mining. Full article

The fermentation of oolong tea is a critical process that determines its quality and flavor. Current fermentation control relies on tea makers’ sensory experience, which is labor-intensive and time-consuming. In this study, using Tieguanyin oolong tea as the research object, features including the tea water loss rate, aroma, image color, and texture were obtained using weight sensors, a tin oxide-type gas sensor, and a visual acquisition system. Support vector regression (SVR), random forest (RF) machine learning, and long short-term memory (LSTM) deep learning algorithms were employed to establish models for assessing the fermentation degree based on both single features and fused multi-source features, respectively. The results showed that in the test set of the fermentation degree models based on single features, the mean absolute error (MAE) ranged from 4.537 to 6.732, the root mean square error (RMSE) ranged from 5.980 to 9.416, and the coefficient of determination (R²) values varied between 0.898 and 0.959. In contrast, the data fusion models demonstrated superior performance, with the MAE reduced to 2.232–2.783, the RMSE reduced to 2.693–3.969, and R² increased to 0.982–0.991, confirming that feature fusion enhanced characterization accuracy. Finally, the Sparrow Search Algorithm (SSA) was applied to optimize the data fusion models. After optimization, the models exhibited a MAE ranging from 1.703 to 2.078, a RMSE from 2.258 to 3.230, and R² values between 0.988 and 0.994 on the test set. The application of the SSA further enhanced model accuracy, with the Fusion-SSA-LSTM model demonstrating the best performance. The research results enable online real-time monitoring of the fermentation degree of Tieguanyin oolong tea, which contributes to the automated production of Tieguanyin oolong tea. Full article

The accurate prediction of PM10 concentrations at smart construction sites is crucial for improving urban air quality, protecting public health, and advancing sustainable development in the construction industry. PM10 concentrations at construction sites are influenced by the interaction of construction intensity and environmental meteorological factors, resulting in nonlinear and volatile data. To improve prediction accuracy, this paper presents a two-stage mode decomposition method that integrates Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD). This method is combined with a Bidirectional Long Short-Term Memory (BiLSTM) neural network, optimized using the Sparrow Search Algorithm (SSA), to establish a hybrid model for forecasting PM10 concentrations at construction sites. Initially, CEEMDAN decomposes the original sequence into several Intrinsic Mode Functions (IMFs). The sample entropy of each component is then calculated, and K-means clustering is used to group them. VMD is applied to further decompose the high-frequency components obtained after clustering. SSA is then employed to optimize the parameters of the BiLSTM network, which models all the components with the optimized predictive model. The predicted values of all components are aggregated to generate the final forecast. Real-time monitoring data from Construction Site A in Nanjing are used for case study validation. The empirical results demonstrate that the proposed hybrid prediction model outperforms comparison models on all evaluation metrics, offering a scientific foundation for sustainable and automated dust reduction decision-making at smart construction sites, thereby facilitating the shift toward greener, smarter, and more digitized construction practices. Full article

Accurate surface area data are imperative for the development of meaningful property–function relationships. Nitrogen gas (N₂) adsorption/Brunauer–Emmet–Teller (BET) surface area analysis is a widely used technique for surface area characterization of materials because of straightforward sample preparation, automation, and low cost. However, iron disulfide (FeS₂) does not typically exhibit quantifiable N₂ monolayer formation in BET measurements. FeS₂ has been applied in fields such as batteries, catalysis, and adsorption, all of which would benefit from techniques that reliably assess surface area (SSA) of the active material. To address this, we evaluated FeS₂ samples by combining alternative surface characterization techniques to quantify SSA. Ten different FeS₂ samples from various manufacturers are characterized via BET, laser diffraction, scanning electron microscopy, non-contact profilometry, and liquid dye adsorption. Compared to BET, which resulted in a wide range of SSAs between 0.049–1.213 m² g⁻¹, liquid dye adsorption was found to be accurate for pyrite samples at low sample masses (<50 mg), with SSA values between 0.99–10.20 m² g⁻¹. Using an optical characterization approach, which combined particle size and surface roughness data, we readily estimated SSA of the particles and found these values correlated linearly with liquid adsorption but not BET values. This work serves to help researchers choose a more fitting method for examining low surface area materials like FeS₂ and can easily be applied to other minerals for quantitative and qualitative surface area comparisons. Full article

For patients suffering from obstructive sleep apnea and sleep-related breathing disorders, snoring is quite common, and it greatly interferes with the quality of life for them and for the people surrounding them. For diagnosing obstructive sleep apnea, snoring is used as a screening parameter, so the exact detection and classification of snoring sounds are quite important. Therefore, automated and very high precision snoring analysis and classification algorithms are required. In this work, initially the features are extracted from six different domains, such as time domain, frequency domain, Discrete Wavelet Transform (DWT) domain, sparse domain, eigen value domain, and cepstral domain. The extracted features are then selected using three efficient feature selection techniques, such as Golden Eagle Optimization (GEO), Salp Swarm Algorithm (SSA), and Refined SSA. The selected features are finally classified with the help of eight traditional machine learning classifiers and two proposed classifiers, such as the Firefly Algorithm-Weighted Extreme Learning Machine hybrid with Adaboost model (FA-WELM-Adaboost) and the Capuchin Search Algorithm-Weighted Extreme Learning Machine hybrid with Adaboost model (CSA-WELM-Adaboost). The analysis is performed on the MPSSC Interspeech dataset, and the best results are obtained when the DWT features with the refined SSA feature selection technique and FA-WELM-Adaboost hybrid classifier are utilized, reporting an Unweighted Average Recall (UAR) of 74.23%. The second-best results are obtained when DWT features are selected with the GEO feature selection technique and a CSA-WELM-Adaboost hybrid classifier is utilized, reporting an UAR of 73.86%. Full article

In the context of rapidly advancing agricultural technology, precise and efficient methods for crop detection and counting play a crucial role in enhancing productivity and efficiency in crop management. Monitoring corn tassels is key to assessing plant characteristics, tracking plant health, predicting yield, and addressing issues such as pests, diseases, and nutrient deficiencies promptly. This ultimately ensures robust and high-yielding corn growth. This study introduces a method for the recognition and counting of corn tassels, using RGB imagery captured by unmanned aerial vehicles (UAVs) and the YOLOv8 model. The model incorporates the Pconv local convolution module, enabling a lightweight design and rapid detection speed. The ACmix module is added to the backbone section to improve feature extraction capabilities for corn tassels. Moreover, the CTAM module is integrated into the neck section to enhance semantic information exchange between channels, allowing for precise and efficient positioning of corn tassels. To optimize the learning rate strategy, the sparrow search algorithm (SSA) is utilized. Significant improvements in recognition accuracy, detection efficiency, and robustness are observed across various UAV flight altitudes. Experimental results show that, compared to the original YOLOv8 model, the proposed model exhibits an increase in accuracy of 3.27 percentage points to 97.59% and an increase in recall of 2.85 percentage points to 94.40% at a height of 5 m. Furthermore, the model optimizes frames per second (FPS), parameters (params), and GFLOPs (giga floating point operations per second) by 7.12%, 11.5%, and 8.94%, respectively, achieving values of 40.62 FPS, 14.62 MB, and 11.21 GFLOPs. At heights of 10, 15, and 20 m, the model maintains stable accuracies of 90.36%, 88.34%, and 84.32%, respectively. This study offers technical support for the automated detection of corn tassels, advancing the intelligence and precision of agricultural production and significantly contributing to the development of modern agricultural technology. Full article

Accurate forecasting remains a challenge, even with advanced techniques like deep learning (DL), ARIMA, and Holt–Winters (H&W), particularly for chaotic phenomena such as those observed in several areas, such as COVID-19, energy, and financial time series. Addressing this, we introduce a Forecasting Method with Filters and Residual Analysis (FMFRA), a hybrid methodology specifically applied to datasets of COVID-19 time series, which we selected for their complexity and exemplification of current forecasting challenges. FMFFRA consists of the following two approaches: FMFRA-DL, employing deep learning, and FMFRA-SSA, using singular spectrum analysis. This proposed method applies the following three phases: filtering, forecasting, and residual analysis. Initially, each time series is split into filtered and residual components. The second phase involves a simple fine-tuning for the filtered time series, while the third phase refines the forecasts and mitigates noise. FMFRA-DL is adept at forecasting complex series by distinguishing primary trends from insufficient relevant information. FMFRA-SSA is effective in data-scarce scenarios, enhancing forecasts through automated parameter search and residual analysis. Chosen for their geographical and substantial populations and chaotic dynamics, time series for Mexico, the United States, Colombia, and Brazil permitted a comparative perspective. FMFRA demonstrates its efficacy by improving the common forecasting performance measures of MAPE by 22.91%, DA by 13.19%, and RMSE by 25.24% compared to the second-best method, showcasing its potential for providing essential insights into various rapidly evolving domains. Full article

The Salp Swarm Algorithm (SSA) is a bio-inspired metaheuristic optimization technique that mimics the collective behavior of Salp chains hunting for food in the ocean. While it demonstrates competitive performance on benchmark problems, the SSA faces challenges with slow convergence and getting trapped in local optima like many population-based algorithms. To address these limitations, this study proposes the locally weighted Salp Swarm Algorithm (LWSSA), which combines two mechanisms into the standard SSA framework. First, a locally weighted approach is introduced and integrated into the SSA to guide the search toward locally promising regions. This heuristic iteratively probes high-quality solutions in the neighborhood and refines the current position. Second, a mutation operator generates new positions for Salp followers to increase randomness throughout the search. In order to assess its effectiveness, the proposed approach was evaluated against the state-of-the-art metaheuristics using standard test functions from the IEEE CEC 2021 and IEEE CEC 2017 competitions. The methodology is also applied to a risk assessment of cardiovascular disease (CVD). Seven optimization strategies of the extreme gradient boosting (XGBoost) classifier are evaluated and compared to the proposed LWSSA-XGBoost model. The proposed LWSSA-XGBoost achieves superior prediction performance with 94% F1 score, 94% recall, 93% accuracy, and 93% area under the ROC curve in comparison with state-of-the-art competitors. Overall, the experimental results demonstrate that the LWSSA enhances SSA’s optimization ability and XGBoost predictive power in automated CVD risk assessment. Full article

The well-known methods of scene extraction on video are focused on analyzing the similarity between frames. However, they do not all analyze the composition of the image scene, which may remain the same during maintenance. Therefore, this paper proposes an algorithm for equipment maintenance scene detection based on human hand tracking. It is based on the assumption that, when servicing technological equipment, it is possible to determine the change in repair action by the position of the service engineer’s hands. Thus, certain information and the algorithm that processes these changes allow us to segment the video into actions performed during the service. We process the time series obtained by moving the hand position using spectral singular value decomposition for multivariate time series. To verify the algorithm, we performed maintenance on the control cabinet of a mining conveyor and recorded the work on a first-person video, which was processed using the developed method. As a result, we obtained some scenes corresponding to opening the control cabinet, de-energizing the unit, and checking the contacts with a multimeter buzzer test. A third-person video of motor service was similarly processed. The algorithm demonstrated the results in separate scenes of removing screws, working with a multimeter, and disconnecting and replacing motor parts. Full article

In this paper, we introduce a new and advanced multi-feature selection method for bacterial classification that uses the salp swarm algorithm (SSA). We improve the SSA’s performance by using opposition-based learning (OBL) and a local search algorithm (LSA). The proposed method has three main stages, which automate the categorization of bacteria based on their unique characteristics. The method uses a multi-feature selection approach augmented by an enhanced version of the SSA. The enhancements include using OBL to increase population diversity during the search process and LSA to address local optimization problems. The improved salp swarm algorithm (ISSA) is designed to optimize multi-feature selection by increasing the number of selected features and improving classification accuracy. We compare the ISSA’s performance to that of several other algorithms on ten different test datasets. The results show that the ISSA outperforms the other algorithms in terms of classification accuracy on three datasets with 19 features, achieving an accuracy of 73.75%. Additionally, the ISSA excels at determining the optimal number of features and producing a better fit value, with a classification error rate of 0.249. Therefore, the ISSA method is expected to make a significant contribution to solving feature selection problems in bacterial analysis. Full article

Financial technology (Fintech) plays a pivotal role in driving contemporary technology, society, economies, and many other fields. The new-generation Fintech is Smart Fintech, mainly empowered and inspired by data science and artificial intelligence (DSAI) technologies. Smart Fintech combines DSAI and transforms finance and economies for driving automated, intelligent, personalized financial and economic businesses, services and systems, and the whole of business. The strength and growth of the country’s economy were evaluated with the accurate prediction of how many companies will succeed and how many will fail. Financial crisis prediction (FCP) has a considerable effect on the economy. Prior research focuses mainly on deep learning (DL), machine learning (ML), and statistical approaches for forecasting the financial health of a company. Thus, this study presents a hybrid hunter–prey optimization with a deep learning-based FCP (HHPODL-FCP) technique. The objective of the HHPODL-FCP algorithm lies in the effective identification of the financial crisis in enterprises or organizations. To accomplish this, the HHPODL-FCP method makes use of the HHPO algorithm for the feature subset selection process. In addition, the HHPODL-FCP technique employs the gated attention recurrent network (GARN) model for the identification and classification of financial and non-financial crises. The HHPODL-FCP method exploits a sparrow search algorithm (SSA)-based hyperparameter tuning process to enrich the performance of the GARN model. The simulation results of the HHPODL-FCP method are tested on different financial datasets. A wide range of experiments highlighted the remarkable performance of the HHPODL-FCP method over recent techniques under various measures. Full article

Singular spectrum analysis (SSA) is a non-parametric adaptive technique used for time series analysis. It allows solving various problems related to time series without the need to define a model. In this study, we focus on the problem of trend extraction. To extract trends using SSA, a grouping of elementary components is required. However, automating this process is challenging due to the nonparametric nature of SSA. Although there are some known approaches to automated grouping in SSA, they do not work well when the signal components are mixed. In this paper, a novel approach that combines automated identification of trend components with separability improvement is proposed. We also consider a new method called EOSSA for separability improvement, along with other known methods. The automated modifications are numerically compared and applied to real-life time series. The proposed approach demonstrated its advantage in extracting trends when dealing with mixed signal components. The separability-improving method EOSSA proved to be the most accurate when the signal rank is properly detected or slightly exceeded. The automated SSA was very successfully applied to US Unemployment data to separate an annual trend from seasonal effects. The proposed approach has shown its capability to automatically extract trends without the need to determine their parametric form. Full article

As much as half or more of deep partial-thickness burn wounds develop hypertrophic scarring and contracture. Once formed, treatments are only minimally effective. Pirfenidone (Pf), indicated for treatment of idiopathic pulmonary fibrosis, is an anti-inflammatory and anti-fibrotic small molecule that potentially can be repurposed as a preventative against scarring in burn wounds. We present a drug-in-matrix patch with a soft skin adhesive (SSA) wound-contacting layer for multi-day drug delivery of Pf into burn wounds at the point of injury. Our patch construction consists of an SSA adhesive layer (Liveo™ MG7-9850, Dupont, Wilmington, DE, USA) for wound fixation, an acrylic co-polymer drug matrix (DURO-TAK 87-2852, Henkel, Düsseldorf, Germany) as the drug (Pf) reservoir, and an outermost protective polyurethane backing. By employing a drug-in-matrix patch design, Pf can be loaded as high as 2 mg/cm². Compared to the acrylic co-polymer adhesive patch preparations and commercial films, adding an SSA layer markedly reduces skin stripping observed under scanning electron microscopy (SEM). Moreover, the addition of varying SSA thicknesses did not interfere with the in vitro release kinetics or drug permeation in ex vivo porcine skin. The Pf patch can be easily applied onto and removed from deep partial-thickness burn wounds on Duroc pigs. Continuous multi-day dosing of Pf by the patches (>200 μg/cm²/day) reduced proinflammatory biomarkers in porcine burn wounds. Pf patches produced by the manual laboratory-scale process showed excellent stability, maintaining intact physical patch properties and in vitro biological activity for up to one year under long-term (25 °C at 60% RH) and 6 months under accelerated (40 °C at 75% RH) test conditions. To manufacture our wound safe-and-extended-release patch, we present scale-up processes using a machine-driven automated roll-to-roll pilot scale coater. Full article

Automated body weight (BW) estimation is an important indicator to reflect the automation level of breeding, which can effectively reduce the damage to animals in the breeding process. In order to manage meat rabbits accurately, reduce the frequency of manual intervention, and improve the intelligent of meat rabbit breeding, this study constructed a meat rabbit weight estimation system to replace manual weighing. The system consists of a meat rabbit image acquisition robot and a weight estimation model. The robot stops at each cage in turn and takes a top view of the rabbit through an RGB camera. The images from the robot are automatically processed in the weight estimation model, which consists of the meat rabbit segmentation network based on improved Mask RCNN and the BW fitting network. Attention mechanism, PointRend algorithm, and improved activation function are proposed to improve the performance of Mask RCNN. Six morphological parameters (relative projected area, contour perimeter, body length, body width, skeleton length, and curvature) are extracted from the obtained mask, and are sent into the BW fitting network based on SVR-SSA-BPNN. The experiment shows that the system achieves a 4.3% relative error and 172.7 g average absolute error in BW estimation for 441 rabbits, while the meat rabbit segmentation network achieves a 99.1% mean average precision (mAP) and a 98.7% mean pixel accuracy (MPA). The system provides technical support for automatic BW estimation of meat rabbits in commercial breeding, which is helpful to promote precision breeding. Full article

Background: Portable electroencephalogram (EEG) systems are often used in health care applications to record brain signals because their ease of use. An electrooculogram (EOG) is a common, low frequency, high amplitude artifact of the eye blink signal that might confuse disease diagnosis. As a result, artifact removal approaches in single EEG portable devices are in high demand. Materials: Dataset 2a from the BCI Competition IV was employed. It contains the EEG data from nine subjects. To determine the EOG effect, each session starts with 5 min of EEG data. This recording lasted for two minutes with the eyes open, one minute with the eyes closed, and one minute with eye movements. Methodology: This article presents the automated removal of EOG artifacts from EEG signals. Circulant Singular Spectrum Analysis (CiSSA) was used to decompose the EOG contaminated EEG signals into intrinsic mode functions (IMFs). Next, we identified the artifact signal components using kurtosis and energy values and removed them using 4-level discrete wavelet transform (DWT). Results: The proposed approach was evaluated on synthetic and real EEG data and found to be effective in eliminating EOG artifacts while maintaining low frequency EEG information. CiSSA-DWT achieved the best signal to artifact ratio (SAR), mean absolute error (MAE), relative root mean square error (RRMSE), and correlation coefficient (CC) of 1.4525, 0.0801, 18.274, and 0.9883, respectively. Comparison: The developed technique outperforms existing artifact suppression techniques according to performance measures. Conclusions: This advancement is important for brain science and can contribute as an initial pre-processing step for research related to EEG signals. Full article