Sample Dataset Research Articles

The U-net-based ice pore parameter extraction method for establishing the SAW icing sensing mechanism

The porous ice layer formed upon the SAW (surface acoustic wave) propagation path will produce transient acoustic attenuation, and a new icing sensing method can be constructed based on this feature. Obtaining the pore characteristics of an ice layer is a prerequisite and basis for deriving the sensing mechanism of SAW icing. Employing the U-net network, a segmentation model of frozen pores is developed by collecting frozen images and calibrating sample data sets for training in this work. The MIOU and the MPA of the model reach 92.16 % and 95.15 % respectively. Then, the watershed algorithm and post-processing were used to accurately obtain the pore characteristic parameters (porosity, pore number, and average pore area) of the ice layer. On this basis, applying the Biot's theory for two-phase porous media, a theoretical model of the SAW icing sensing mechanism was established, and the acoustic sensing response under different icing types was theoretically simulated. To prove the accuracy of the theoretical simulation, a SAW sensor using a waveguide structure of SU-8/ST-90 °X quartz operating at 80 MHz was constructed and evaluated experimentally. The results demonstrate that the acoustic sensing responses of different ice types are completely consistent with the theoretical results. This fully verifies the accuracy of the ice pore parameters extracted in this work and also confirms the feasibility of using pore microscopic information to achieve ice detection and ice type discrimination.

A Method for Identifying the Wear State of Grinding Wheels Based on VMD Denoising and AO-CNN-LSTM

Monitoring the condition of the grinding wheel in real-time during the grinding process is crucial as it directly impacts the precision and quality of the workpiece. Deep learning technology plays a vital role in analyzing the changes in sensor signals and identifying grinding wheel wear during the grinding process. Therefore, this paper innovatively proposes a grinding wheel wear recognition method based on Variational Mode Decomposition (VMD) denoising and Aquila Optimizer—Convolutional Neural Network—Long Short-Term Memory (AO-CNN-LSTM). The paper utilizes Acoustic Emission (AE) signals generated during grinding to identify the condition of the grinding wheel. To address noise interference, the study introduces the VMD algorithm for denoising the sample dataset, enhancing the effectiveness of neural network training. Subsequently, the dataset is fed into the designed Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM) structure with AO-optimized parameters. Experimental results demonstrate that this method achieves high accuracy and performance.

Hierarchical Bayesian adaptive lasso methods on exponential random graph models

The analysis of network data has become an increasingly prominent and demanding field across multiple research fields including data science, health, and social sciences, requiring the development of robust models and efficient computational methods. One well-established and widely employed modeling approach for network data is the Exponential Random Graph Model (ERGM). Despite its popularity, there is a recognized necessity for further advancements to enhance its flexibility and variable selection capabilities. To address this need, we propose a novel hierarchical Bayesian adaptive lasso model (BALERGM), which builds upon the foundations of the ERGM. The BALERGM leverages the strengths of the ERGM and incorporates the flexible adaptive lasso technique, thereby facilitating effective variable selection and tackling the inherent challenges posed by high-dimensional network data. The model improvements have been assessed through the analysis of simulated data, as well as two authentic datasets. These datasets encompassed friendship networks and a respondent-driven sampling dataset on active and healthy lifestyle awareness programs.

User authentication system based on human exhaled breath physics.

This work, in a pioneering approach, attempts to build a biometric system that works purely based on the fluid mechanics governing exhaled breath. We test the hypothesis that the structure of turbulence in exhaled human breath can be exploited to build biometric algorithms. This work relies on the idea that the extrathoracic airway is unique for every individual, making the exhaled breath a biomarker. Methods including classical multi-dimensional hypothesis testing approach and machine learning models are employed in building user authentication algorithms, namely user confirmation and user identification. A user confirmation algorithm tries to verify whether a user is the person they claim to be. A user identification algorithm tries to identify a user's identity with no prior information available. A dataset of exhaled breath time series samples from 94 human subjects was used to evaluate the performance of these algorithms. The user confirmation algorithms performed exceedingly well for the given dataset with over 97% true confirmation rate. The machine learning based algorithm achieved a good true confirmation rate, reiterating our understanding of why machine learning based algorithms typically outperform classical hypothesis test based algorithms. The user identification algorithm performs reasonably well with the provided dataset with over 50% of the users identified as being within two possible suspects. We show surprisingly unique turbulent signatures in the exhaled breath that have not been discovered before. In addition to discussions on a novel biometric system, we make arguments to utilise this idea as a tool to gain insights into the morphometric variation of extrathoracic airway across individuals. Such tools are expected to have future potential in the area of personalised medicines.

3D medical image segmentation based on semi-supervised learning using deep co-training

In recent years, artificial intelligence has been applied to 3D COVID-19 medical image diagnosis, which reduces detection costs and missed diagnosis rates with higher predictive accuracy, and diagnostic efficiency. However, the limited size and low quality of clinical 3D medical image samples have hindered the segmentation performance of 3D models. Therefore, we propose a 3D medical image segmentation model based on semi-supervised learning using co-training. Multi-view and multi-modal images are generated using spatial flipping and windowing techniques to enhance the spatial diversity of 3D image samples. A pseudo label generation module based on confidence-weights is employed to generate reliable pseudo labels for non-annotated data, thereby increasing the sample size and reducing overfitting. The proposed approach utilizes a three-stage training process: firstly, training a single network based on annotated data; secondly, incorporating non-annotated data to train a dual-modal network and generate pseudo labels; finally, jointly training six models in three dimensions using both annotated and pseudo labels generated from multi-view and multi-modal images, aiming to enhance segmentation accuracy and generalization performance. Additionally, a consistency regularization loss is applied to reduce noises and accelerate convergence of the training. Moreover, a heatmap visualization method is employed to focus on the attention of features at each stage of training, providing effective reference for clinical diagnosis. Experiments were conducted on an open dataset of 3D COVID-19 CT samples and a non-annotated dataset from TCIA, including 771 NIFTI-format CT images from 661 COVID-19 patients. The results of 5-fold cross-validation show that the proposed model achieves a segmentation accuracy of Dice=73.30 %, ASD=10.633, Sensitivity=63.00 %, and Specificity=99.60 %. Compared to various typical semi-supervised learning 3D segmentation models, it demonstrates better segmentation accuracy and generalization performance.

RUL Prediction for Piezoelectric Vibration Sensors Based on Digital-Twin and LSTM Network

Piezoelectric vibration sensors (PVSs) are widely used in high-temperature environments, such as vibration measurements in aero-engines, because of their high accuracy, small size, and high temperature resistance. Accurate prediction of its RUL (Remaining Useful Life) is essential for applying and maintaining PVSs. Based on PVSs’ characteristics and main failure modes, this work combines the Digital-Twin (DT) and Long Short-Term Memory (LSTM) networks to predict the RUL of PVSs. In this framework, DT can provide rich data collection, analysis, and simulation capabilities, which have advantages in RUL prediction, and LSTM network has good results in predicting time sequence data. The proposed method exploits the advantages of those techniques in feature data collection, sample optimization, and RUL multiclassification. To verify the prediction of this method, a DT platform is established to conduct PVS degradation tests, which generates sample datasets, then the LSTM network is trained and validated. It has been proved that prediction accuracy is more than 99.7%, and training time is within 94 s. Based on this network, the RUL of PVSs is predicted using different test samples. The results show that the method performed well in prediction accuracy, sample data utilization, and compatibility.

Traumatic Brain Injury and Risk of Schizophrenia and Other Non-mood Psychotic Disorders: Findings From a Large Inpatient Database in the United States.

Traumatic brain injury (TBI) is linked with an increased risk of schizophrenia and other non-mood psychotic disorders (psychotic disorders), but the prevalence and contributing factors of these psychiatric conditions post-TBI remain unclear. This study explores this link to identify key risk factors in TBI patients. We used the 2017 National Inpatient Sample dataset. Patients with a history of TBI (n = 26 187) were identified and matched 1:1 by age and gender to controls without TBI (n = 26 187). We compared clinical and demographic characteristics between groups. The association between TBI and psychotic disorders was explored using the logistic regression analysis, and results were presented as Odds ratio (OR) and 95% confidence interval (CI). Psychotic disorders were significantly more prevalent in TBI patients (10.9%) vs controls (4.7%) (P < .001). Adjusted odds of psychotic disorders were 2.2 times higher for TBI patients (95% CI 2.05-2.43, P < .001). Male TBI patients had higher psychotic disorders prevalence than females (11.9% vs 8.4%). Younger age, bipolar disorder, anxiety disorders, substance abuse, personality disorders, and intellectual disability are associated with an increased risk of psychotic disorders in men. Our study found that hospitalized TBI patients had 2.2 times higher odds of Schizophrenia non-mood psychotic disorder, indicating an association. This highlights the need for early screening of psychotic disorders and intervention in TBI patients, calling for more research.

An active learning method using deep adversarial autoencoder-based sufficient dimension reduction neural network for high-dimensional reliability analysis

Reliability analysis often requires time-consuming evaluations, especially when dealing with high-dimensional and nonlinear problems. To address this challenge, surrogate model methods are frequently employed. One way to improve the efficiency of surrogate model methods involves selecting informative samples that significantly enhance the accuracy of the surrogate model. This paper introduces a novel approach to facilitate the construction of surrogate models and selection of informative samples in high-dimensional reliability analysis, through an active learning method based on a deep adversarial autoencoder-based sufficient dimension reduction (AAE-SDR) neural network. The AAE-SDR neural network serves as a surrogate model, transforming complex high-dimensional variables into tractable, low-dimensional embeddings relevant to the target. These embeddings are Gaussian-distributed with a distinct latent limit state boundary. A new sampling strategy is proposed to select informative misclassified samples by iteratively identifying candidate samples near the latent limit state boundary and uniformly sampling from the candidate sample dataset based on the latent Gaussian distribution. The effectiveness of the proposed approach is demonstrated through two high-dimensional numerical examples and a cable-stayed bridge case study. Results show that the proposed method simplifies complex high-dimensional reliability problems and provides a relatively accurate estimated failure probability with a limited number of samples.

Determination of sugar in tangerines by fluorescence with an Improved partial least squares (PLS) algorithm

The accurate determination of sugar content in tangerines plays a pivotal role in assessing their quality, nutritional value, and marketability. Traditional methods for sugar quantification often involve time-consuming and resource-intensive processes. In this paper, we introduce a novel approach for sugar determination in tangerines utilizing fluorescence spectroscopy in conjunction with an improved Partial Least Squares (iPLS) algorithm. A robust testing model was developed, incorporating a diverse dataset of tangerine samples with known sugar concentrations. Fluorescence spectra were acquired for 80 samples, of which 37 were used to build the iPLS model and were considered as the training dataset. The remaining 43 samples served as the validation dataset and were used to show the model’s efficacy. The training dataset was evaluated using cross-validation, and F-values were computed to determine how many main components should be utilized to build the model. The result approved validation dataset’s R-square and root-mean-square error were 0.9777 and 0.002992, respectively. These findings open the door to broader applications in the citrus industry and beyond, with the potential for automating the analysis process and improving overall quality control.

A novel approach based on spatio-temporal attention and multi-scale modeling for mechanical failure prediction

Accurately predicting the remaining useful life (RUL) of equipment is crucial for planning production and eliminating unplanned downtime events. Specifically, the application of effective RUL prediction methods can detect potential equipment failures in advance to provide timely maintenance measures, which can help enterprises better plan and manage resources, optimize production plans, and provide strong support for subsequent maintenance decisions. The data-driven approaches have achieved great success in the field of RUL prediction by fully exploiting mechanical degradation information from historical operation data. However, these approaches have certain limitations, for instance, (1) they always fail to precisely extract spatial and temporal features in noisy environments simultaneously; (2) they often fail to effectively capture local features and global degradation trends simultaneously. To overcome the above limitations, we design an end-to-end model, termed ASATCN-TABGRU, for mechanical failure prediction, which contains an automatic shrinking attention temporal convolutional network (ASATCN) and a temporal attention bidirectional gated recurrent unit (TABGRU). In ASATCN module, to extract spatio-temporal information from historical operation data, we first perform a multi-scale modeling of historical operation data through a deliberately designed dilated causal convolution subnetwork (DCCS) to obtain local features. Then, we propose a novel soft thresholding subnetwork (STS) based on the normalization-based attention module (NAM), to capture useful temporal features through the automatic shrinking soft thresholding mechanism from the local features sequence; in addition, we design a hybrid attention subnetwork (HAS) to capture spatial features with flexible and different importance by the spatial-channel attention mechanism from historical operation data. The precise extraction of spatio-temporal features is then achieved through a connection operation. With the above encoded spatio-temporary features sequence, a TABGRU module is further proposed to capture global degradation trends by simultaneously extracting contextual information and historical influence information, thereby effectively modeling the local and global features. The experiments show that our approach has better performance and robustness, compared with other state-of-the-art approaches, particularly on the small sample dataset.

Comparison and Evaluation of Five Global Land Cover Products on the Tibetan Plateau

The Tibetan Plateau (TP) region contains maximal alpine grassland ecology at the mid-latitudes. This region is also recognized as an ecologically fragile and sensitive area under the effects of global warming. Regional climate modeling and ecosystem research depend on accurate land cover (LC) information. In order to obtain accurate LC information over the TP, the reliability and precision of five moderate/high-resolution LC products (MCD12Q1, C3S-LC, GlobeLand30, GLC_FCS30, and ESA2020 in 2020) were analyzed and evaluated in this study. The different LC products were compared with each other in terms of areal/spatial consistency and assessed with four reference sample datasets (Geo-Wiki, GLCVSS, GOFC-GOLD, and USGS) using the confusion matrix method for accuracy evaluation over the TP. Based on the paired comparison of these five LC datasets, all five LC products show that grass is the major land cover type on the TP, but the range of grass coverage identified by the different products varies noticeably, from 43.35% to 65.49%. The fully consistent spatial regions account for 43.72% of the entire region of the TP, while, in the transition area between grass and bare soil, there is still a large area of medium-to-low consistency. In addition, a comparison of LC datasets using integrated reference datasets shows that the overall accuracies of MCD12Q1, C3S-LC, GlobeLand30, GLC_FCS30, and ESA2020 are 54.29%, 49.32%, 53.03%, 53.73%, and 60.11%, respectively. The producer accuracy of the five products is highest for grass, while glaciers have the most reliable and accurate characteristics among all LC products for users. These findings provide valuable insights for the selection of rational and appropriate LC datasets for studying land-atmosphere interactions and promoting ecological preservation in the TP.

Face Mask Detection Based on Improved YOLOv8

The detection of face mask wear is one of the essential measures to prevent the spread of infectious diseases in public places. In order to balance the is-sues of inference speed and performance of target detection models on em-bedded devices, this paper proposes a face mask detection based on the im-proved YOLOv8 algorithm, YOLOv8n-SLIM-DYHEAD. By improving the YOLOv8n algorithm, the balance between detection time and accuracy is-sues is achieved. The Mosaic data augmentation method is used to increase the detection targets of various sizes, enrich the sample dataset of masks of various scales. On the neck network, the Slim-neck structure is used to fuse features of different sizes extracted by the leading network, reducing the complexity of the model while maintaining accuracy. In the detection layer, DyHead is used to integrate better feature diversity caused by target scale differences and target shape position differences. Experimental results show that the improved algorithm YOLOv8n-SLIM-DYHEAD has increased the mAP @0.5 and mAP @0.5:0.95 of the original YOLOv8n algorithm by 2.1 and 5.5 percentage points, respectively. In addition, the complexity and pa-rameters of the model have remained relatively high, and it can accurately detect the wearing of masks in real-time.

Algorithm of face anti-spoofing based on pseudo-negative features generation.

Despite advancements in face anti-spoofing technology, attackers continue to pose challenges with their evolving deceptive methods. This is primarily due to the increased complexity of their attacks, coupled with a diversity in presentation modes, acquisition devices, and prosthetic materials. Furthermore, the scarcity of negative sample data exacerbates the situation by causing domain shift issues and impeding robust generalization. Hence, there is a pressing need for more effective cross-domain approaches to bolster the model's capability to generalize across different scenarios. This method improves the effectiveness of face anti-spoofing systems by analyzing pseudo-negative sample features, expanding the training dataset, and boosting cross-domain generalization. By generating pseudo-negative features with a new algorithm and aligning these features with the use of KL divergence loss, we enrich the negative sample dataset, aiding the training of a more robust feature classifier and broadening the range of attacks that the system can defend against. Through experiments on four public datasets (MSU-MFSD, OULU-NPU, Replay-Attack, and CASIA-FASD), we assess the model's performance within and across datasets by controlling variables. Our method delivers positive results in multiple experiments, including those conducted on smaller datasets. Through controlled experiments, we demonstrate the effectiveness of our method. Furthermore, our approach consistently yields favorable results in both intra-dataset and cross-dataset evaluations, thereby highlighting its excellent generalization capabilities. The superior performance on small datasets further underscores our method's remarkable ability to handle unseen data beyond the training set.

The integration of single-cell and bulk RNA-seq atlas reveals ERS-mediated acinar cell damage in acute pancreatitis

BackgroundAcute pancreatitis (AP) is a clinically common acute abdominal disease, whose pathogenesis remains unclear. The severe patients usually have multiple complications and lack specific drugs, leading to a high mortality and poor outcome. Acinar cells are recognized as the initial site of AP. However, there are no precise single-cell transcriptomic profiles to decipher the landscape of acinar cells during AP, which are the missing pieces of jigsaw we aimed to complete in this study.MethodsA single-cell sequencing dataset was used to identify the cell types in pancreas of AP mice and to depict the transcriptomic maps in acinar cells. The pathways’ activities were evaluated by gene sets enrichment analysis (GSEA) and single-cell gene sets variation analysis (GSVA). Pseudotime analysis was performed to describe the development trajectories of acinar cells. We also constructed the protein–protein interaction (PPI) network and identified the hub genes. Another independent single-cell sequencing dataset of pancreas samples from AP mice and a bulk RNA sequencing dataset of peripheral blood samples from AP patients were also analyzed.ResultsIn this study, we identified genetic markers of each cell type in the pancreas of AP mice based on single-cell sequencing datasets and analyzed the transcription changes in acinar cells. We found that acinar cells featured acinar-ductal metaplasia (ADM), as well as increased endocytosis and vesicle transport activity during AP. Notably, the endoplasmic reticulum stress (ERS) and ER-associated degradation (ERAD) pathways activated by accumulation of unfolded/misfolded proteins in acinar cells could be pivotal for the development of AP.ConclusionWe deciphered the distinct roadmap of acinar cells in the early stage of AP at single-cell level. ERS and ERAD pathways are crucially important for acinar homeostasis and the pathogenesis of AP.

On Integrating Time-Series Modeling with Long Short-Term Memory and Bayesian Optimization: A Comparative Analysis for Photovoltaic Power Forecasting

The means of energy generation are rapidly progressing as production shifts from a centralized model to a fully decentralized one that relies on renewable energy sources. Energy generation is intermittent and difficult to control owing to the high variability in the weather parameters. Consequently, accurate forecasting has gained increased significance in ensuring a balance between energy supply and demand with maximum efficiency and sustainability. Despite numerous studies on this issue, large sample datasets and measurements of meteorological variables at plant sites are generally required to obtain a higher prediction accuracy. In practical applications, we often encounter the problem of insufficient sample data, which makes it challenging to accurately forecast energy production with limited data. The Holt–Winters exponential smoothing method is a statistical tool that is frequently employed to forecast periodic series, owing to its low demand for training data and high forecasting accuracy. However, this model has limitations, particularly when handling time-series analysis for long-horizon predictions. To overcome this shortcoming, this study proposes an integrated approach that combines the Holt–Winters exponential smoothing method with long short-term memory and Bayesian optimization to handle long-range dependencies. For illustrative purposes, this new method is applied to forecast rooftop photovoltaic production in a real-world case study, where it is assumed that measurements of meteorological variables (such as solar irradiance and temperature) at the plant site are not available. Through our analysis, we found that by utilizing these methods in combination, we can develop more accurate and reliable forecasting models that can inform decision-making and resource management in this field.

Synthetic data augmentation for high-resolution X-ray welding defect detection and classification based on a small number of real samples

Deep learning has become the dominant technology in most computer vision tasks. These methods often rely on a large number of labeled sample datasets for training, and in the field of non-destructive testing of welds in industrial manufacturing, weld images with defects are very scarce, and it is still a challenging challenge to construct high-resolution weld defect datasets that meet the requirements. To overcome this limitation, a new data augmentation method for high-resolution X-ray welding defect classification and synthesis based on a small number of real samples is proposed to realize the data augmentation of industrial nondestructive inspection X-ray film defect images. Firstly, to overcome the scarcity of the weld X-ray defect classification dataset, the weld X-ray defect classification dataset (Weld Defect Classification, WDC) is constructed. Secondly, the performance of 16 common deep classification models on WDC datasets is explored. Then, the images of the real local welding defects and the non-defective weld area are fused at random locations, and two data augmentation modes, (Single Image Single Defect, SISD) and (Single Image Multi Defects, SIMD), can generate defect files and annotation files (Visual Object Classes, VOC) at the same time, which can save a lot of time for manual marking. Finally, compared with the traditional data augmentation method, the proposed method can effectively improve the accuracy of defect detection and generalization, the mAP (Mean Average Precision, mAP) @0.5 of YOLOV8X (You Only Look Once, YOLO) and YOLOV5.6.1X is 66.6% and 72.8%, which provides an effective solution for data sample generation in the industrial field.

RETRACTED: ODRNN: Optimized Deep Recurrent Neural Networks for Automatic Detection of Leukaemia

Leukaemia, a kind of cancer that may occur in individuals of all ages, including kids and adults, is a significant contributor to worldwide death rates. This illness is currently diagnosed by manual evaluation of blood samples obtained using microscopic imaging, which is frequently slower, lengthy, imprecise. Additionally, inspection under a microscope, leukemic cells look and develop similarly to normal cells, making identification more difficult. Convolutional Neural Networks (CNN) for Deep Learning has provided cutting-edge techniques for picture classification challenges throughout the previous several decades, there is still potential for development with regard to performance, effectiveness, and learning technique. As a consequence, the study provided a unique deep learning approach known as Optimized Deep Recurrent Neural Network (ODRNN) for identifying Leukaemia sickness by analysing microscopic images of blood samples. Deep recurrent neural networks (DRNN) are used in the recommended strategy for diagnosing Leukaemia, then the Red Deer Optimization algorithm (RDOA) applies to optimize the weight gained by DRNN. The mass of DRNN from RDOA will be tuned on the deer roaring rate behavior. The model that has been proposed is evaluated on two openly accessible Leukaemia blood sample datasets, AML, ALL_IDB1 and ALL_IDB2. It is possible to create an accurate computer-aided diagnosis for Leukaemia malignancy by using the proposed deep learning model, which shows encouraging results. The research work uses statistical metrics related to disease including specificity, recall, accuracy, precision and F1 score to assess the effectiveness of the proposed model for identification and classification. The proposed method achieves highly impressive results, with scores of 98.96%, 99.85%, 99.98%, 99.23%, and 99.98%, respectively.

SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion

Objective. Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from Computed Tomography (CT) scans to address the efficacy issue of honeycomb lung segmentation. Methods. This study proposes a sparse mapping-based graph representation segmentation network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask. Results. Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47). Significance. The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis, and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

Investigating the Role of Machine Leaning and Blockchain for Forecasting Stock Market Trends

There is a sudden deluge of evolutionary approaches in the domain of data processing and computation, which are significantly affecting several facets of applications globally. Artificial intelligence, machine learning and Blockchain happen to be at the forefront of evolutionary computation beating conventional approaches. Finance applications currently are heavily reliant of data driven models. Stock trend analysis happens to be one such approach, which lays the foundation for forecasting decisions to be made. The leeway in such applications is critically small as minimal inaccuracies in forecasting may lead to major losses. This paper presents the current perspective in terms of evolutionary algorithms such as artificial intelligence and Blockchain and how they are transforming software development, the application of machine learning algorithms to regression problems. Finally, the stock trend analysis based on in and out of sample datasets has been performed for standard S&amp;P datasets. A comparative analysis with previous work clearly indicates the improved performance of the proposed work with respect to baseline approaches in the domain.

LIRRN: Location-Independent Relative Radiometric Normalization of Bitemporal Remote-Sensing Images.

Relative radiometric normalization (RRN) is a critical pre-processing step that enables accurate comparisons of multitemporal remote-sensing (RS) images through unsupervised change detection. Although existing RRN methods generally have promising results in most cases, their effectiveness depends on specific conditions, especially in scenarios with land cover/land use (LULC) in image pairs in different locations. These methods often overlook these complexities, potentially introducing biases to RRN results, mainly because of the use of spatially aligned pseudo-invariant features (PIFs) for modeling. To address this, we introduce a location-independent RRN (LIRRN) method in this study that can automatically identify non-spatially matched PIFs based on brightness characteristics. Additionally, as a fast and coregistration-free model, LIRRN complements keypoint-based RRN for more accurate results in applications where coregistration is crucial. The LIRRN process starts with segmenting reference and subject images into dark, gray, and bright zones using the multi-Otsu threshold technique. PIFs are then efficiently extracted from each zone using nearest-distance-based image content matching without any spatial constraints. These PIFs construct a linear model during subject-image calibration on a band-by-band basis. The performance evaluation involved tests on five registered/unregistered bitemporal satellite images, comparing results from three conventional methods: histogram matching (HM), blockwise KAZE, and keypoint-based RRN algorithms. Experimental results consistently demonstrated LIRRN's superior performance, particularly in handling unregistered datasets. LIRRN also exhibited faster execution times than blockwise KAZE and keypoint-based approaches while yielding results comparable to those of HM in estimating normalization coefficients. Combining LIRRN and keypoint-based RRN models resulted in even more accurate and reliable results, albeit with a slight lengthening of the computational time. To investigate and further develop LIRRN, its code, and some sample datasets are available at link in Data Availability Statement.