Artificial Features Research Articles

Wavelength-Controlled Photoconductance Polarity Switching via Harnessing Defects in Doped PdSe2 for Artificial Synaptic Features.

Optoelectronic synapses are currently drawing significant attention as fundamental building blocks of neuromorphic computing to mimic brain functions. In this study, a two-terminal synaptic device based on a doped PdSe2 flake is proposed to imitate the key neural functions in an optical pathway. Due to the wavelength-dependent desorption of oxygen clusters near the intrinsic selenide vacancy defects, the doped PdSe2 photodetector achieves a high negative photoresponsivity of -7.8 × 103 A W-1 at 473nm and a positive photoresponsivity of 181 A W-1 at 1064nm. This wavelength-selective bi-direction photoresponse endows an all-optical pathway to imitate the fundamental functions of artificial synapses on a device level, such as psychological learning and forgetting capability, as well as dynamic logic functions. The underpinning photoresponse is further demonstrated on a flexible platform, providing a viable technology for neuromorphic computing in wearable electronics. Furthermore, the p-type doping results in an effective increase of the channel's electrical conductivity and a significant reduction in power consumption. Such low-power-consuming optical synapses with simple device architecture and low-dimensional features demonstrate tremendous promise for building multifunctional artificial neuromorphic systems in the future.

Correlation between AI-based CT organ features and normal lung dose in adjuvant radiotherapy following breast-conserving surgery: a multicenter prospective study

BackgroundRadiation pneumonitis (RP) is one of the common side effects after adjuvant radiotherapy in breast cancer. Irradiation dose to normal lung was related to RP. We aimed to propose an organ features based on deep learning (DL) model and to evaluate the correlation between normal lung dose and organ features.MethodsPatients with pathology-confirmed invasive breast cancer treated with adjuvant radiotherapy following breast-conserving surgery in four centers were included. From 2019 to 2020, a total of 230 patients from four nationwide centers in China were screened, of whom 208 were enrolled for DL modeling, and 22 patients from another three centers formed the external testing cohort. The subset of the internal testing cohort (n = 42) formed the internal correlation testing cohort for correlation analysis. The outline of the ipsilateral breast was marked with a lead wire before the scanning. Then, a DL model based on the High-Resolution Net was developed to detect the lead wire marker in each slice of the CT images automatically, and an in-house model was applied to segment the ipsilateral lung region. The mean and standard deviation of the distance error, the average precision, and average recall were used to measure the performance of the lead wire marker detection model. Based on these DL model results, we proposed an organ feature, and the Pearson correlation coefficient was calculated between the proposed organ feature and ipsilateral lung volume receiving 20 Gray (Gy) or more (V20).ResultsFor the lead wire marker detection model, the mean and standard deviation of the distance error, AP (5 mm) and AR (5 mm) reached 3.415 ± 4.529, 0.860, 0.883, and 4.189 ± 8.390, 0.848, 0.830 in the internal testing cohort and external testing cohort, respectively. The proposed organ feature calculated from the detected marker correlated with ipsilateral lung V20 (Pearson correlation coefficient, 0.542 with p < 0.001 in the internal correlation testing cohort and 0.554 with p = 0.008 in the external testing cohort).ConclusionsThe proposed artificial Intelligence-based CT organ feature was correlated with normal lung dose in adjuvant radiotherapy following breast-conserving surgery in patients with invasive breast cancer.Trial registrationNCT05609058 (08/11/2022).

HRRSODN: high-Resolution remote sensing object detection network fusion of road-adjacent relationships

Application of deep learning technology in remote sensing image target detection(RSITD)has made remarkable progress in recent years. However, existing methods usually fuse spatial context information at the pixel level while ignoring the mining of spatial relationships between ground objects. This paper proposes a high-resolution remote sensing object detection network fusion of road-adjacent relationships (HRRSODN) that integrates road proximity relations. Taking artificial features such as toll stations adjacent to roads as an example, the spatial relationship of road proximity is used to assist visual information and improve the extraction accuracy. The method optimizes detection by: Using the spatial relationship as prior information; fusing coordinate attention that captures the spatial relationship between objects; and adding the attention generated by the spatial relationship to the attention generated in the original X and Y directions. This enables the model to understand the spatial layout of objects in the image. The distance loss function concretizes the spatial relationship into a distance index. The distance loss is incorporated into the training process by measuring the spatial distance between feature targets. Thus, during training, the network focuses not only on the positional information of the targets but also pays more attention to the spatial layout of the features. Experimental results show that, compared with conventional methods, the proposed method has achieved significant improvements in detection performance and mining spatial relationships. This verifies the importance of considering the spatial relationship of ground objects in remote sensing target detection. Further, this paper proposes a new method for target detection in remote sensing images (RSIs), which effectively utilizes the spatial relationship information between targets, and provides a new idea for further improving target detection in RSI.

Analytical Validation of the PreciseDx Digital Prognostic Breast Cancer Test in Early-Stage Breast Cancer

BackgroundPreciseDx Breast (PDxBr) is a digital test that predicts early-stage breast cancer recurrence within 6-years of diagnosis. Materials and MethodsUsing hematoxylin and eosin-stained whole slide images of invasive breast cancer (IBC) and artificial intelligence-enabled morphology feature array, microanatomic features are generated. Morphometric attributes in combination with patient's age, tumor size, stage, and lymph node status predict disease free survival using a proprietary algorithm. Here, analytical validation of the automated annotation process and extracted histologic digital features of the PDxBr test, including impact of methodologic variability on the composite risk score is presented. Studies of precision, repeatability, reproducibility and interference were performed on morphology feature array-derived features. The final risk score was assessed over 20-days with 2-operators, 2-runs/day, and 2-replicates across 8-patients, allowing for calculation of within-run repeatability, between-run and within-laboratory reproducibility. ResultsAnalytical validation of features derived from whole slide images demonstrated a high degree of precision for tumor segmentation (0.98, 0.98), lymphocyte detection (0.91, 0.93), and mitotic figures (0.85, 0.84). Correlation of variation of the assay risk score for both reproducibility and repeatability were less than 2%, and interference from variation in hematoxylin and eosin staining or tumor thickness was not observed demonstrating assay robustness across standard histopathology preparations. ConclusionIn summary, the analytical validation of the digital IBC risk assessment test demonstrated a strong performance across all features in the model and complimented the clinical validation of the assay previously shown to accurately predict recurrence within 6-years in early-stage invasive breast cancer patients.

Defect identification method for ultrasonic inspection of pipeline welds based on cross-modal zero-shot learning

Ultrasonic inspection of pipeline welds still uses the traditional visual inspection signal method to identify pipeline defects. The identification of defects relies entirely on the subjective judgment of practitioners and is highly dependent on their level of experience. Deep learning models have achieved very good results in classification tasks, but they rely on a large number of annotated data samples for each category. However, it is difficult to collect a large number of samples with different defects and annotate them for the classification of pipe welding defects. Based on the idea of zero-shot learning (ZSL), which makes full use of experts’ semantic descriptions of defect categories, artificial semantic features are integrated cross-modally with ultrasonic inspection signal features. In this way, a common semantic space containing seen and unseen classes is constructed to achieve the detection of various defects. Meanwhile, to alleviate the problem of extreme imbalance of training data between the seen and unseen classes in ZSL model training, a ZSL model Feature-GAN-ZSL (FGZ) fused with a generative adversarial network (GAN) is proposed. The model utilizes a Feature-GAN network to generate unseen class features during training and adds a classifier to enhance the generation of features with stronger discriminative power. In the experiments, sample data for porosity, incomplete penetration, and cracks were used as visible classes, and samples for incomplete fusion and slag entrapment were used as unseen classes. Five state-of-the-art models in the ZSL domain were compared. The results show that the FGZ model has a good ability to recognize various defects, not only the types of defects that participated in the training but also the defects that did not participate in the training. This plays a perfect role in dealing with various pipeline welding defects.

ERP: SAP S/4HANA Cloud RISE Enterprise Solution Automation with Artificial Intelligence Features

Abstract: Cloud computing has experienced significant growth in recent years for business transformation, with an increasing number of applications migrating to the cloud, where they can centrally manage a wide range of resources, including hardware and software. SAP S/4HANA Cloud is a next-generation ERP system that is built on the SAP Cloud Platform. It offers a number of advantages over traditional on-premises ERP systems. SAP S/4HANA Cloud is a strategic move for organizations aiming to enhance their ERP capabilities and embrace the digital future. SAP RISE is a cloud-based enterprise resource planning (ERP) solution that combines the power of SAP S/4HANA Cloud with artificial intelligence (AI) and machine learning (ML) capabilities. S/4HANA Cloud migration and AI integration is a powerful combination that can help businesses of all sizes to achieve their transformation goals and stay ahead of the competition. By migrating to S/4HANA Cloud and integrating AI features, businesses can improve their operational efficiency, increase their agility, accelerate their innovation, and reduce their costs. In this paper, author has explained the requirement of SAP S/4HANA Cloud RISE Enterprise Solution Automation with Artificial Intelligence features – a current business transformation needs to achieve business goal.

PDHF: Effective phishing detection model combining optimal artificial and automatic deep features

Currently, the increasing number of high-volume phishing attacks is among the largest threats to networking environments on a daily basis. During such a severe attack, researchers prefer to extract numerous features to improve the accuracy of phishing detection. However, the redundant features that may exist in the extracted feature set may be adapted by phishing attackers, not only degrading detection performance but also shortening the effective time of the constructed detection models. To address these problems, this study proposes phishing detection based on hybrid features (PDHF), a novel phishing detection model based on a combination of optimal artificial and automatic deep learning features. The optimal artificial phishing features are obtained by removing redundant features based on the newly designed feature importance evaluation index and an improved bidirectional search algorithm. To extend the effective time of phishing detection, deep features are learned from URLs using a one-dimensional character convolutional neural network (CNN) and a disorderly quantized attention mechanism. The experimental results show that PDHF outperforms many state-of-the-art methods and achieves an accuracy of 0.9965, precision of 0.9942, recall of 0.9940, and F1-score of 0.9941. These results can help in the development of a security plug-in for clients, browsers, and various instant messaging tools that run on network edges, personal computers, smartphones, and other personal terminals.

Gearbox Compound Fault Diagnosis in Edge-IoT Based on Legendre Multiwavelet Transform and Convolutional Neural Network

The application of edge computing combined with the Internet of Things (edge-IoT) has been rapidly developed. It is of great significance to develop a lightweight network for gearbox compound fault diagnosis in the edge-IoT context. The goal of this paper is to devise a novel and high-accuracy lightweight neural network based on Legendre multiwavelet transform and multi-channel convolutional neural network (LMWT-MCNN) to fast recognize various compound fault categories of gearbox. The contributions of this paper mainly lie in three aspects: The feature images are designed based on the LMWT frequency domain and they are easily implemented in the MCNN model to effectively avoid noise interference. The proposed lightweight model only consists of three convolutional layers and three pooling layers to further extract the most valuable fault features without any artificial feature extraction. In a fully connected layer, the specific fault type of rotating machinery is identified by the multi-label method. This paper provides a promising technique for rotating machinery fault diagnosis in real applications based on edge-IoT, which can largely reduce labor costs. Finally, the PHM 2009 gearbox and Paderborn University bearing compound fault datasets are used to verify the effectiveness and robustness of the proposed method. The experimental results demonstrate that the proposed lightweight network is able to reliably identify the compound fault categories with the highest accuracy under the strong noise environment compared with the existing methods.

Impacts of sights and sounds on anxiety relief in the high-density city

Anxiety is one of the most common mental health disorders in the world. Although acoustic and visual environments are known to influence many other aspects of mental health, we know little about their independent and interactive effects on the levels of anxiety of high-density city dwellers. We conducted a laboratory experiment using a two-way factorial design (four visual environments × five acoustic environments) and randomly assigned participants to 20 treatment conditions. Before exposure to a condition, they engaged in the Trier Social Stress Test to induce a moderate level of anxiety. A total of 223 urban dwellers reported their anxiety level before and after a randomly assigned environmental treatment. The results showed that acoustic and visual environments had significantly interactive influence on anxiety relief. The impact of acoustic environments on anxiety relief was 4.67 times greater than the impact of visual environments. Environments with more natural features, regardless of whether they were acoustic or visual, played a greater role in reducing anxiety than environments with more artificial features. The combination of green scenes and fully natural sounds gave a significantly greater anxiety relief than any other acoustic-visual environments. The implications of these results for planning and design in high-density cities are discussed.

Predicting Energy Generation in Large Wind Farms: A Data-Driven Study with Open Data and Machine Learning

Wind energy has become a trend in Brazil, particularly in the northeastern region of the country. Despite its advantages, wind power generation has been hindered by the high volatility of exogenous factors, such as weather, temperature, and air humidity, making long-term forecasting a highly challenging task. Another issue is the need for reliable solutions, especially for large-scale wind farms, as this involves integrating specific optimization tools and restricted-access datasets collected locally at the power plants. Therefore, in this paper, the problem of forecasting the energy generated at the Praia Formosa wind farm, an eco-friendly park located in the state of Ceará, Brazil, which produces around 7% of the state’s electricity, was addressed. To proceed with our data-driven analysis, publicly available data were collected from multiple Brazilian official sources, combining them into a unified database to perform exploratory data analysis and predictive modeling. Specifically, three machine-learning-based approaches were applied: Extreme Gradient Boosting, Random Forest, and Long Short-Term Memory Network, as well as feature-engineering strategies to enhance the precision of the machine intelligence models, including creating artificial features and tuning the hyperparameters. Our findings revealed that all implemented models successfully captured the energy-generation trends, patterns, and seasonality from the complex wind data. However, it was found that the LSTM-based model consistently outperformed the others, achieving a promising global MAPE of 4.55%, highlighting its accuracy in long-term wind energy forecasting. Temperature, relative humidity, and wind speed were identified as the key factors influencing electricity production, with peak generation typically occurring from August to November.

Evaluating the Feasibility and Acceptance of a Mobile Clinical Decision Support System in a Resource-Limited Country: Exploratory Study.

In resource-limited countries, access to specialized health care services such as dermatology is limited. Clinical decision support systems (CDSSs) offer innovative solutions to address this challenge. However, the implementation of CDSSs is commonly associated with unique challenges. VisualDx-an exemplar CDSS-was recently implemented in Botswana to provide reference materials in support of the diagnosis and management of dermatological conditions. To inform the sustainable implementation of VisualDx in Botswana, it is important to evaluate the intended users' perceptions about the technology. This study aims to determine health care workers' acceptance of VisualDx to gauge the feasibility of future adoption in Botswana and other similar health care systems. The study's design was informed by constructs of the Technology Acceptance Model. An explanatory, sequential, mixed methods study involving surveys and semistructured interviews was conducted. The REDCap (Research Electronic Data Capture; Vanderbilt University) platform supported web-based data capture from March 2021 through August 2021. In total, 28 health care workers participated in the study. Descriptive statistics were generated and analyzed using Excel (Microsoft Corp), and thematic analysis of interview transcripts was performed using Delve software. All survey respondents (N=28) expressed interest in using mobile health technology to support their work. Before VisualDx, participants referenced textbooks, journal articles, and Google search engines. Overall, participants' survey responses showed their confidence in VisualDx (18/19, 95%); however, some barriers were noted. Frequently used VisualDx features included generating a differential diagnosis through manual entry of patient symptoms (330/681, 48.5% of total uses) or using the artificial intelligence feature to analyze skin conditions (150/681, 22% of total uses). Overall, 61% (17/28) of the survey respondents were also interviewed, and 4 thematic areas were derived. Participants' responses indicated their willingness to accept VisualDx. The ability to access information quickly without internet connection is crucial in resource-constrained environments. Selected enhancements to VisualDx may further increase its feasibility in Botswana. Study findings can serve as the basis for improving future CDSS studies and innovations in Botswana and similar resource-limited countries.

Badminton video action recognition based on time network

With the continuous development of artificial intelligence research, computer vision research has shifted from traditional “feature engineering”-based methods to deep learning-based “network engineering” methods, which automatically extracts and classifies features by using deep neural networks. Traditional methods based on artificial design features are computationally expensive and are usually used to solve simple research problems, which is not conducive for large-scale data feature extraction. Deep learning-based methods greatly reduce the difficulty of artificial features by learning features from large-scale data and are successfully applied in many visual recognition tasks. Video action recognition methods also shift from traditional methods based on artificial design features to deep learning-based methods, which is oriented to building more effective deep neural network models. Through collecting and sorting related research results found that academic for timing segment network of football and basketball video action research is relatively rich, but lack of badminton research given the above research results, this study based on timing segment network of badminton video action identification can enrich the research results, provide reference for follow-up research. This paper introduces the lightweight attention mechanism into the temporal segmentation network, forming the attention mechanism-timing segmentation network, and trains the neural network to get the classifier of badminton stroke action, which can be predicted as four common types: forehand stroke, backhand stroke, overhead stroke and pick ball. The experimental results show that the recognition recall and accuracy of various stroke movements reach more than 86%, and the average size of recall and accuracy is 91.2% and 91.6% respectively, indicating that the method based on timing segmentation network can be close to the human judgment level and can effectively conduct the identification task of badminton video strokes.

Reorganizing the Waterscape: Asymmetric Loss of Wetlands and Gain of Artificial Water Features in a Mixed-use Watershed

Between the 1780 and 1980s, more than half of the wetlands in the conterminous US were lost. As wetlands have been lost, numerous artificial water features (AWFs), such as stormwater retention ponds, golf course water features, and reservoirs, have been constructed. We contrasted the loss of wetland area and perimeter to the gain of AWF area and perimeter and further explored how this transformation has altered the spatial characteristics of the waterscape. We conducted this analysis in the Tampa Bay Watershed, a large coastal watershed that lost 33% of its wetland area between the 1950s-2007. Trends have been towards fewer, smaller wetlands and more, smaller AWFs. The loss of wetland area far exceeds the gain in AWF area, leading to an overall loss of 23% of the combined wetland and AWF area. However, the loss of wetland perimeter almost equals the gain in AWF perimeter, leading to an overall loss of just 2% of the combined wetland and AWF perimeter. The loss of wetlands and gain of AWFs have predominantly occurred in different geographic locations, with the loss of wetlands predominantly in the headwaters and the gain in AWFs predominantly adjacent to Tampa Bay. Wetlands became further apart, though generally retained their natural distribution, while AWFs became closer to one another and now mirror the more natural wetland distribution. Overall, the physical structure of the waterscape of today is different than in the past, which likely reflects a change in functions performed and related ecological services provided at local and landscape scales.

Real-time path planning based on improved artificial potential field method

Nowadays, with the development of robotics-related technology, its applications permeate many aspects of work and life; In product manufacturing and assembly, tech companies switch from manual to robot automation which improves the production volume and reduces the assembly time. In the tertiary sector including health and social work, the robots learn how to interact with people to meet specified requirements. Path planning constitutes a critical module of robotics engineering that aims to provide the optimal solution for the robot to reach its target point. The artificial potential field methods, refers to APF, are widely used to realize path planning due to their simplicity of calculation and effectiveness in obstacle avoidance. However, the traditional artificial potential field method features the local minimum and oscillation, and unreachable target point problems that make it hard for robots to reach the target point. Based on the weaknesses, an improved version of the gravitation and repulsion force function was introduced in this paper. In addition, the concept of safety distance also contributed to the path planning for robots. Through the simulation experiment, it was shown that the improved APF algorithm successfully addressed the local minima and unreachable target point problem, which could navigate robots to arrive at the destination in both 2D and 3D space by avoiding collision with obstacles.

Robot-in-the-loop: Prototyping robotic digitisation at the Natural History Museum

The Natural History Museum, London (NHM) is home to an impressive collection of over 80 million specimens, of which just 5.5 million have been digitised. Like all similar collections, digitisation of these specimens is very labour intensive, requiring time-consuming manual handling. Each specimen is extracted from its curatorial unit, placed for imaging, labels are manually manipulated, and then returned to storage. Thanks to the NHM’s team of digitisers, workflows are becoming more efficient as they are refined. However, many of these workflows are highly repetitive and ideally suited to automation. The museum is now exploring integrating robots into the digitisation process. The NHM has purchased a Techman TM5 900 robotic arm, equipped with integrated Artificial Intelligence (AI) software and additional features such as custom grippers and a 3D scanner. This robotic arm combines advanced imaging technologies, machine learning algorithms, and robotic manipulation capabilities to capture high-quality specimen data, making it possible to digitise vast collections efficiently (Fig. 1). We showcase the NHM's application of robotics for digitisation, outlining the use cases developed for implementation and the prototypical workflows already in place at the museum. We will explore our invasive and non-invasive digitisation experiments, the many challenges, and the initial results of our early experiments with this transformative technology.

Topology optimization of porous structures by considering acoustic and mechanical characteristics

Porous structures are widely found in nature and have been extensively studied due to their high stiffness-to-weight ratio, excellent sound absorption, and robustness regarding loading variation. This paper proposes a new topology optimization approach for the design of porous acoustic-mechanical structures based on the three-field floating projection topology optimization (FPTO) method. In order to capture the change of ambiguous structural boundary during topology optimization, the mixed displacement/pressure (u/p) finite element formulation with the linear material interpolation scheme is adopted. The artificial porous features of the structures are generated by imposing the local volume constraint defined by a constant or adaptive filter radius. The 0/1 constraints of the design variables are simulated by the floating projection constraint so that the final design has a clear topology. To verify the effectiveness of the proposed method, some interesting 2D and 3D numerical examples considering their mechanical and acoustic characteristics simultaneously are presented to achieve porous structures by minimizing dynamic compliance, possibly with an additional acoustic constraint. The results also show that the resulting porous features are useful in improving the acoustic performance of the optimized designs.

River connectivity increases the diversity of fish communities in gravel pit lakes

AbstractObjectiveOff‐channel floodplain features are important components of a river system that provide habitat and boost regional species pools, but river–floodplain connectivity is disrupted by anthropogenic activities. The Campbell Lakes in Harrison, Ohio, are formerly isolated gravel pits along the Whitewater River and are connected to the river through flooding‐related erosion. The lakes were first stocked with sport fish by Great Parks of Hamilton County to promote recreational fishing, but stocking ended in 2019 due to frequent connection with the Whitewater River during high flow. We explored how the fish community composition of the Campbell Lakes reflects increasing connectivity with the Whitewater River and among the lakes.MethodsUsing historical aerial photographs and river discharge estimates, we established an approximate timeline of permanent connectivity and potential breaches between the lakes and the Whitewater River from 2000 to 2020. Fish community data collected via electrofishing surveys of the Campbell Lakes in 2004, 2007, 2012, and 2020 were compared to data from surveys of the Whitewater and Great Miami rivers in 1995 and 2013.ResultThe lakes were dominated by centrarchid species in early surveys but showed increased species and family richness with time. Based on an analysis of similarity and nonmetric multidimensional scaling, the lakes' fish communities differed significantly among years and gradually increased in resemblance to the river communities.ConclusionOur results suggest that the Campbell Lakes fish communities are broadening to include taxa from the Whitewater and Great Miami River communities and are shifting from lentic to lotic species. The change in fish community assemblages in the Campbell Lakes demonstrates the potential for gravel pit lakes to serve as artificial floodplain features that can enhance river–floodplain connectivity.

Composite receptive fields in the mouse auditory cortex.

A central question in sensory neuroscience is how neurons represent complex natural stimuli. This process involves multiple steps of feature extraction to obtain a condensed, categorical representation useful for classification and behaviour. It has previously been shown that central auditory neurons in the starling have composite receptive fields composed of multiple features. Whether this property is an idiosyncratic characteristic of songbirds, a group of highly specialized vocal learners or a generic property of sensory processing is unknown. To address this question, we have recorded responses from auditory cortical neurons in mice, and characterized their receptive fields using mouse ultrasonic vocalizations (USVs) as a natural and ethologically relevant stimulus and pitch-shifted starling songs as a natural but ethologically irrelevant control stimulus. We have found that these neurons display composite receptive fields with multiple excitatory and inhibitory subunits. Moreover, this was the case with either the conspecific or the heterospecific vocalizations. We then trained the sparse filtering algorithm on both classes of natural stimuli to obtain statistically optimal features, and compared the natural and artificial features using UMAP, a dimensionality-reduction algorithm previously used to analyse mouse USVs and birdsongs. We have found that the receptive-field features obtained with both types of the natural stimuli clustered together, as did the sparse-filtering features. However, the natural and artificial receptive-field features clustered mostly separately. Based on these results, our general conclusion is that composite receptive fields are not a unique characteristic of specialized vocal learners but are likely a generic property of central auditorysystems. KEY POINTS: Auditory cortical neurons in the mouse have composite receptive fields with several excitatory and inhibitory features. Receptive-field features capture temporal and spectral modulations of natural stimuli. Ethological relevance of the stimulus affects the estimation of receptive-field dimensionality.

Exploring Relationships between Boltzmann Entropy of Images and Building Classification Accuracy in Land Cover Mapping.

Remote sensing images are important data sources for land cover mapping. As one of the most important artificial features in remote sensing images, buildings play a critical role in many applications, such as population estimation and urban planning. Classifying buildings quickly and accurately ensures the reliability of the above applications. It is known that the classification accuracy of buildings (usually indicated by a comprehensive index called F1) is greatly affected by image quality. However, how image quality affects building classification accuracy is still unclear. In this study, Boltzmann entropy (an index considering both compositional and configurational information, simply called BE) is employed to describe image quality, and the potential relationships between BE and F1 are explored based on images from two open-source building datasets (i.e., the WHU and Inria datasets) in three cities (i.e., Christchurch, Chicago and Austin). Experimental results show that (1) F1 fluctuates greatly in images where building proportions are small (especially in images with building proportions smaller than 1%) and (2) BE has a negative relationship with F1 (i.e., when BE becomes larger, F1 tends to become smaller). The negative relationships are confirmed using Spearman correlation coefficients (SCCs) and various confidence intervals via bootstrapping (i.e., a nonparametric statistical method). Such discoveries are helpful in deepening our understanding of how image quality affects building classification accuracy.

Whitewater Sound Dependence on Discharge and Wave Configuration at an Adjustable Wave Feature

AbstractStream acoustics has been proposed as a means of monitoring discharge and wave hazards from outside the stream channel. To better understand the dependence of sound on discharge and wave characteristics, this study analyzes discharge and infrasound data from an artificial wave feature which is adjusted to accommodate daily changes in recreational use and seasonal changes in irrigation demand. Monitorable sound is only observed when discharge exceeds ∼35 m3/s, and even above that threshold the sound‐discharge relationship is non‐linear and inconsistent. When sound is observed, it shows consistent dependence on wave type within a given year, but the direction of this dependence varies among the 3 years studied (2016, 2021, and 2022). These findings support previous research that establishes discharge and stream morphology as relevant controls on stream acoustics and highlights the complex, combined effects of these variables.