Global Classification Research Articles

Electronic Workflow for High-Fidelity Clinical Simulation in Nursing.

Recognizing the importance of following the International Nursing Association for Clinical Simulation and Learning Standards: Healthcare Simulation Standards of Best Practice to ensure a successful simulation-based experience, this study aimed to update an electronic workflow created to guide teachers in the development and conduct of a clinical simulation for undergraduate nursing students, according to the latest evidence published in the International Nursing Association for Clinical Simulation and Learning Standards; implement it for online access; and describe the results of its usability criteria evaluation. It is a technological production and study of quantitative nature, descriptive and exploratory. The workflow was reconfigured according to the Contextualized Instructional Design model. The usability criteria analysis occurred through the application of a questionnaire to 23 undergraduate nursing courses professors. It was possible to identify that the technology reached high levels of global classification among faculty, being classified as "excellent" (M [SD], 81.9 [14.9]) by the final score. In view of the results obtained, it is concluded that the Electronic Workflow for High-Fidelity Clinical Simulation in Nursing can serve as a reference to promote the best simulation-based learning for professional training in nursing.

Decision Key-Value Feature Construction for Multihoming Big Data Network

The random forest algorithm under the MapReduce framework has too many redundant and irrelevant features, low training feature information, and low parallelization efficiency when dealing with multihoming big data network problems, so parallelism is based on information theory, and norms is proposed for random forest algorithm (PRFITN). In this paper, the technique used first builds a hybrid dimensional reduction approach (DRIGFN) focused on information gain and the Frobenius norm, successfully reducing the number of redundant and irrelevant features; then, an information theory feature is offered. This results in the dimensionality-reduced dataset. Finally, a technique is suggested in the Reduce stage. The features are grouped in the FGSIT strategy, and the stratified sampling approach is employed to assure the information quantity of the training features in the building of the decision tree in the random forest. When datasets are provided as key/value pairs, it is common to want to aggregate statistics across all objects with the same key. To acquire global classification results and achieve a rapid and equal distribution of key-value pairs, a key-value pair redistribution method (RSKP) is used, which improves the cluster’s parallel efficiency. The approach provides a superior classification impact in multihoming large data networks, particularly for datasets with numerous characteristics, according to the experimental findings. We can utilize feature selection and feature extraction together. In addition to minimizing overfitting and redundancy, lowering dimensionality contributes to improved human interpretation and cheaper computing costs through model simplicity.

The Development of Dark Hyperspectral Absolute Calibration Model Using Extended Pseudo Invariant Calibration Sites at a Global Scale: Dark EPICS-Global

This research aimed to develop a novel dark hyperspectral absolute calibration (DAHAC) model using stable dark targets of “Global Cluster-36” (GC-36), one of the clusters from the “300 Class Global Classification”. The stable dark sites were identified from GC-36 called “Dark EPICS-Global” covering the surface types viz. dark rock, volcanic area, and dark sand. The Dark EPICS-Global shows a temporal variation of 0.02 unit reflectance. This work used the Landsat-8 (L8) Operational Land Imager (OLI), Sentinel-2A (S2A) Multispectral Instrument (MSI), and Earth Observing One (EO-1) Hyperion data for the DAHAC model development, where well-calibrated L8 and S2A were used as the reference sensors, while EO-1 Hyperion with a 10 nm spectral resolution was used as a hyperspectral library. The dark hyperspectral dataset (DaHD) was generated by combining the normalized hyperspectral profile of L8 and S2A for the DAHAC model development. The DAHAC model developed in this study takes into account the solar zenith and azimuth angles, as well as the view zenith and azimuth angles in Cartesian coordinates form. This model is capable of predicting TOA reflectance in all existing spectral bands of any sensor. The DAHAC model was then validated with the Landsat-7 (L7), Landsat-9 (L9), and Sentinel-2B (S2B) satellites from their launch dates to March 2022. These satellite sensors vary in terms of their spectral resolution, equatorial crossing time, spatial resolution, etc. The comparison between the DAHAC model and satellite measurements showed an accuracy within 0.01 unit reflectance across the overall spectral band. The proposed DAHAC model uncertainty level was determined using Monte Carlo simulation and found to be 0.04 and 0.05 unit reflectance for the VNIR and SWIR channels, respectively. The DAHAC model double ratio was used as a tool to perform the inter-comparison between two satellites. The sensor inter-comparison results for L8 and L9 showed a 2% difference and 1% for S2A and S2B across all spectral bands.

Cross-walking personality disorder types to ICD-11 trait domains: An overview of current findings.

The ICD-11 has adopted a classification of Personality Disorders (PD) that abolishes the established categorical PD types in favor of global severity classification with specification of individual trait domains. To facilitate and guide this profound transition, an overview of current research on empirical associations between established PD types and ICD-11 trait domains seems warranted. We identified a total of 9 relevant studies from 2018 to 2022, which were based on both clinical and community samples from U.S., China, Brazil, Denmark, Spain, Korea, and Canada. The patterns of associations with ICD-11 trait domains were systematically synthesized and portrayed for each PD type. Findings overall showed expected and conceptually meaningful associations between categorical PD types and ICD-11 trait domains, with only few deviations. Based on these findings, we propose a cross-walk for translating categorical PD types into ICD-11 trait domains. More research is needed in order to further guide continuity and translation between ICD-10 and ICD-11 PD classification in mental healthcare, including facet-level ICD-11 trait information. Moreover, the nine reviewed studies only relied on self-reported ICD-11 trait domains, which should be expanded with clinician-rated trait domains in future research. Finally, future research should also take ICD-11's essential PD severity classification into account.

Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes

AbstractMapping wetland types in northern‐latitude regions with Earth Observation (EO) data is important for several practical and scientific applications, but at the same time challenging due to the variability and dynamic nature in wetland features introduced by differences in geophysical conditions. The objective of this study was to better understand the ability of Sentinel‐1 radar data, Sentinel‐2 optical data and terrain derivatives derived from Copernicus digital elevation model to distinguish three main peatland types, two upland classes, and surface water, in five contrasting landscapes located in the northern parts of Alaska, Canada and Scandinavia. The study also investigated the potential benefits for classification accuracy of using regional classification models constructed from region‐specific training data compared to a global classification model based on pooled reference data from all five sites. Overall, the results show high promise for classifying peatland types and the three other land cover classes using the fusion approach that combined all three EO data sources (Sentinel‐1, Sentinel‐2 and terrain derivatives). Overall accuracy for the individual sites ranged between 79.7% and 90.3%. Class specific accuracies for the peatland types were also high overall but differed between the five sites as well as between the three classes bog, fen and swamp. A key finding is that regional classification models consistently outperformed the global classification model by producing significantly higher classification accuracies for all five sites. This suggests for progress in identifying effective approaches for continental scale peatland mapping to improve scaling of for example, hydrological‐ and greenhouse gas‐related processes in Earth system models.

Support Vector Machine-Based Global Classification Model of the Toxicity of Organic Compounds to Vibrio fischeri.

Vibrio fischeri is widely used as the model species in toxicity and risk assessment. For the first time, a global classification model was proposed in this paper for a two-class problem (Class - 1 with log1/IBC50 ≤ 4.2 and Class + 1 with log1/IBC50 > 4.2, the unit of IBC50: mol/L) by utilizing a large data set of 601 toxicity log1/IBC50 of organic compounds to Vibrio fischeri. Dragon software was used to calculate 4885 molecular descriptors for each compound. Stepwise multiple linear regression (MLR) analysis was used to select the descriptor subset for the models. The ten molecular descriptors used in the classification model reflect the structural information on the Michael-type addition of nucleophiles, molecular branching, molecular size, polarizability, hydrophobic, and so on. Furthermore, these descriptors were interpreted from the point of view of toxicity mechanisms. The optimal support vector machine (SVM) model (C = 253.8 and γ = 0.009) was obtained with the genetic algorithm. The SVM classification model produced a prediction accuracy of 89.1% for the training set (451 log1/IBC50), of 80.0% for the test set (150 log1/IBC50), and of 86.9% for the total data set (601 log1/IBC50), which are higher than that (80.5%, 76%, and 79.4%, respectively) from the binary logistic regression (BLR) model. The global SVM classification model is successful, although it deals with a large data set in relation to the toxicity of organics to Vibrio fischeri.

Reassessing climate classification for buildings under climate change: Indian context

Climate classification is essential for buildings because it influences the planning and design of a building, its orientation, building geometry and design of building envelopes such as walls, roofs and openings. In the event of climate change, the existing classifications must be revised or updated to provide both proper guidelines for the design and construction of buildings and adaptation strategies for the existing buildings. The study attempted a comprehensive review of the existing global and Indian classification of climates on buildings. The paper analysed the existing Indian climate classification to include the climate change scenarios by studying 310 locations. The warming trend observed in the locations establishes a need for revision in classification.

Detection of Generative Linguistic Steganography Based on Explicit and Latent Text Word Relation Mining Using Deep Learning

Covert communication channels can be easily constructed using text steganography based on social media. Offenders can easily utilize these channels to engage in various criminal activities, which brings great challenges in maintaining the security of cyberspace. Among the text information hiding methods, generative linguistic steganography poses the biggest threat to network security because it does not need the original carrier and has high embedding efficiency. The existing generative linguistic steganalysis methods fail to deeply mine text word relation, hence the detection performance is relatively unsatisfactory. In this paper, we prove that there is explicit and latent steganography-sensitive text word relation. Based on this, we propose a generative linguistic steganalysis method based on Explicit and Latent text word relation Mining, named ELM. Firstly, we employ a distributed readin module to convert words into real number vectors. Then, MRA (Mining Relation by Attentions) is proposed to mine the explicit and latent text word relation. Finally, global adaptive classification module is presented to exploit the mined relation feature to predict whether secret information is embedded in the current text segment. Experimental results demonstrate that the detection performance of ELM is better than the existing generative linguistic steganalysis methods.

Living Donor Liver Transplantation Alone Is Not Inferior to Combined Kidney Liver Transplant for Cirrhotic Patients With Chronic Kidney Disease

Chronic kidney disease (CKD) is common in patients with chronic liver disease (CLD) as is acute kidney injury (AKI). The differentiation between CKD vs AKI is often difficult and sometimes the both may coexist. A combined kidney-liver transplant (CKLT) may result in a kidney transplant in patients whose renal function is likely to recover or at least who have stable renal function post-transplant. We retrospectively enrolled 2742 patients who underwent living donor liver transplant at our center from 2007 to 2019. This audit was carried out in liver transplant recipients with CKD 3 to 5 who underwent either liver transplant alone (LTA) or CKLT to look at outcomes and long-term evolution of renal function. Forty-seven patients met the medical eligibility criteria for CKLT. Of the 47 patients, 25 underwent LTA and the rest 22 underwent CKLT. The diagnosis of CKD was made according to the Kidney Disease: Improving Global Outcomes classification. Preoperative renal function parameters were comparable between the 2 groups. However, CKLT patients had significantly lower glomerular filtration rates (P=.007) and higher proteinuria (P=.01). Postoperatively, renal function, and comorbidities were comparable between the 2 groups. Survival was similar at 1, 3, and 12 months, respectively (log-rank; P=.84,=.81, and=.96, respectively). At the end of the study period, 57% of patients who survived in LTA groups had stabilized renal function (Creatinine=1.8 ± 0.6 mg/dL). Liver transplant alone is not inferior to CKLT in living donor situations. Renal dysfunction is stabilized in the long term whereas long-term dialysis may be carried out in others. Living donor liver transplantation alone is not inferior to CKLT for cirrhotic patients with CKD.

Drought stress identification of tomato plant using multi-features of hyperspectral imaging and subsample fusion.

Drought stress (DS) is one of the most frequently occurring stresses in tomato plants. Detecting tomato plant DS is vital for optimizing irrigation and improving fruit quality. In this study, a DS identification method using the multi-features of hyperspectral imaging (HSI) and subsample fusion was proposed. First, the HSI images were measured under imaging condition with supplemental blue lights, and the reflectance spectra were extracted from the HSI images of young and mature leaves at different DS levels (well-watered, reduced-watered, and deficient-watered treatment). The effective wavelengths (EWs) were screened by the genetic algorithm. Second, the reference image was determined by ReliefF, and the first four reflectance images of EWs that are weakly correlated with the reference image and mutually irrelevant were obtained using Pearson's correlation analysis. The reflectance image set (RIS) was determined by evaluating the superposition effect of reflectance images on identification. The spectra of EWs and the image features extracted from the RIS by LeNet-5 were adopted to construct DS identification models based on support vector machine (SVM), random forest, and dense convolutional network. Third, the subsample fusion integrating the spectra and image features of young and mature leaves was used to improve the identification further. The results showed that supplemental blue lights can effectively remove the high-frequency noise and obtain high-quality HSI images. The positive effect of the combination of spectra of EWs and image features for DS identification proved that RIS contains feature information pointing to DS. Global optimal classification performance was achieved by SVM and subsample fusion, with a classification accuracy of 95.90% and 95.78% for calibration and prediction sets, respectively. Overall, the proposed method can provide an accurate and reliable analysis for tomato plant DS and is hoped to be applied to other crop stresses.

Mapping Fire Severity in Southwest China Using the Combination of Sentinel 2 and GF Series Satellite Images.

Fire severity mapping can capture heterogeneous fire severity patterns over large spatial extents. Although numerous remote sensing approaches have been established, regional-scale fire severity mapping at fine spatial scales (<5 m) from high-resolution satellite images is challenging. The fire severity of a vast forest fire that occurred in Southwest China was mapped at 2 m spatial resolution by random forest models using Sentinel 2 and GF series remote sensing images. This study demonstrated that using the combination of Sentinel 2 and GF series satellite images showed some improvement (from 85% to 91%) in global classification accuracy compared to using only Sentinel 2 images. The classification accuracy of unburnt, moderate, and high severity classes was significantly higher (>85%) than the accuracy of low severity classes in both cases. Adding high-resolution GF series images to the training dataset reduced the probability of low severity being under-predicted and improved the accuracy of the low severity class from 54.55% to 72.73%. RdNBR was the most important feature, and the red edge bands of Sentinel 2 images had relatively high importance. Additional studies are needed to explore the sensitivity of different spatial scales satellite images for mapping fire severity at fine spatial scales across various ecosystems.

A Phylogenetic and Morphological Evolution Study of Ribes L. in China Using RAD-Seq

Ribes L. belongs to the Grossulariaceae family and has important edible, medicinal, ornamental, and landscaping values. Taxonomic classification within this genus is difficult due to its large variety of species, wide distribution, large morphological variations, and presence of two complex taxonomic groups with bisexual or unisexual flowers. Our study aims to clarify the phylogenetic relationships of Ribes L. taxa in China, and further, to provide a reference for a revised global classification of it. The phylogenetic analysis of 52 Ribes L. samples from 30 species was constructed based on restriction site-associated DNA sequencing and single nucleotide polymorphisms. Afterward, two important taxonomic characters were selected for ancestral state reconstruction over the molecular phylogeny. The results showed that the 52 samples could be divided into six branches, i.e., six subgenera, which caused some controversy regarding the morphological classification of Ribes L. in China. The molecular phylogeny supported the separation of subg. Coreosma from subg. Ribesia and subg. Hemibotrya from subg. Berisia and validated the rationale for recognizing subg. Grossularia as an independent subgenus, the rationality of which was further verified by the reconstruction of ancestor traits. Gene flow among Ribes L. was identified and further confirmed our results.

Seasonal quiet-day morphology of VLF signal strength at Ibadan

Very Low Frequency (VLF) signal amplitude is enhanced during solar flare events. Hence, it can be used as remote sensing for tracking solar flares and studying the lower ionosphere. However, the enhancement is not directly proportional to the magnitude of a solar flare hindering the effectiveness of the VLF signal as a remote sensor for tracking solar flare. Preliminary analysis shows that the level of enhancement recorded for a particular solar flare occurrence depends on the background fluctuations. Thus, this study aims to explore the background fluctuations of the VLF signal using quiet-day data and investigate the impact of background fluctuations on solar flare detectability using the VLF signal. The VLF data used for this study were collected using a VLF receiver installed at KolaDaisi University, Ibadan (KDU-I). The VLF data were from three stations; GBZ (Freq.: 19.8 kHz, Lat.: 21.82°, Long.: 114.17°), NWC (Freq.: 19.58 kHz, Lat.: 54.91°, Long.: 003.28°) and VTX4 (Freq.: 19.2, kHz Lat.: 08.38°, Long.: 077.75°) recorded between 2019 and 2022 at Ibadan (Lat.: 7.6248°, Long.: 3.9131°). The results revealed that the time series has a cyclic pattern that corresponds to each global season classification in the northern hemisphere (Summer, autumn, winter and spring) with an upward trend from wet to dry season. This observation shows that similar geophysical parameters that drive meteorology also have an impact on the background fluctuations of VLF amplitude. It was also observed that the sensitivity of VLF amplitude in sensing solar flare depends on the background fluctuation. It is recommended that the effect of meteorology and background fluctuation be considered when modelling VLF amplitude as a remote sensor for tracking solar flares.

Bioclimatic change as a function of global warming from CMIP6 climate projections

Abstract. Climate change is predicted to lead to major changes in terrestrial ecosystems. However, substantial differences in climate model projections for given scenarios of greenhouse gas emissions continue to limit detailed assessment. Here we show, using a traditional Köppen–Geiger bioclimate classification system, that the latest CMIP6 Earth system models actually agree well on the fraction of the global land surface that would undergo a major change per degree of global warming. Data from “historical” and “SSP585” model runs are used to create bioclimate maps at various degrees of global warming and to investigate the performance of the multi-model ensemble mean when classifying climate data into discrete categories. Using a streamlined Köppen–Geiger scheme with 13 classifications, global bioclimate classification maps at 2 and 4 K of global warming above a 1901–1931 reference period are presented. These projections show large shifts in bioclimate distribution, with an almost exclusive change from colder, wetter bioclimates to hotter, drier ones. Historical model run performance is assessed and examined by comparison with the bioclimatic classifications derived from the observed climate over the same time period. The fraction (f) of the land experiencing a change in its bioclimatic class as a function of global warming (ΔT) is estimated by combining the results from the individual models. Despite the discrete nature of the bioclimatic classification scheme, we find only a weakly saturating dependence of this fraction on global warming f =1-e-0.14ΔT, which implies about 13 % of land experiencing a major change in climate per 1 K increase in global mean temperature between the global warming levels of 1 and 3 K. Therefore, we estimate that stabilizing the climate at 1.5 K rather than 2 K of global warming would save over 7.5 million square kilometres of land from a major bioclimatic change.

Galaxy ASIST: A web-based platform for mapping and assessment of global standards of antimicrobial susceptibility: A case study in Acinetobacter baumannii genomes.

Antimicrobial susceptibility testing (AST) is used to determine the susceptibility of an organism to antibiotics. The determination of susceptibility is based on MIC breakpoints and is provided by EUCAST and CLSI. Likewise, phenotypic classification criteria developed by CDC/ECDC are used for the classification of pathogens into susceptible, multidrug-resistant, extremely drug-resistant, or totally drug-resistant categories. Whole-genome sequencing (WGS)-based diagnosis is now supplementing existing gold-standard microbiology methods for rapid and more precise AST, and therefore, EUCAST recommended quality criteria to assess whole-genome sequence for reporting the same. In this study, these three global standards, MIC breakpoints, phenotypic classification, and genome quality, are applied to the largest publicly available data for Acinetobacter baumannii (AB), the most critical priority pathogen identified by WHO. The drug sensitivity profile and genomes for isolates of AB were obtained from PATRIC and evaluated with respect to AST standards (CLSI and EUCAST). Whole genome quality assessment and antimicrobial resistance mapping is performed with QUAST and ABRicate, respectively. Four in-house methods are developed for mapping standards and are integrated into a Galaxy workflow based system, Galaxy-ASIST. Analysis of the extent of agreement between CLSI 2022 and EUCAST 2022 for antibiotics was carried out using Cohen's kappa statistics. An automated pipeline, Galaxy-ASIST, is designed and developed for the characterization of clinical isolates based on these standards. Evaluation of over 6,500 AB strains using Galaxy-ASIST indicated that only 10% of the publicly available datasets have metadata to implement these standards. Furthermore, given that CLSI and EUCAST have different MIC breakpoints, discrepancies are observed in the classification of resistant and susceptible isolates following these standards. It is, therefore, imperative that platforms are developed that allow the evaluation of ever increasing phenotypic and genome sequence datasets for AST. Galaxy-ASIST offers a centralized repository and a structured metadata architecture to provide a single globally acceptable framework for AST profiling of clinical isolates based on global standards. The platform also offers subsequent fine mapping of antimicrobial-resistant determinants. Galaxy-ASIST is freely available at https://ab-openlab.csir.res.in/asist.

A federated semi‐supervised learning approach for network traffic classification

SummaryThe classification of network traffic, which involves classifying and identifying the type of network traffic, is the most fundamental step to network service improvement and modern network management. Classic machine learning and deep learning methods have widely adopted in the field of network traffic classification. However, there are two major challenges in practice. One is the user privacy concern in cross‐domain traffic data sharing for the purpose of training a global classification model, and the other is the difficulty to obtain large amount of labeled data for training. In this paper, we propose a novel approach using federated semi‐supervised learning for network traffic classification, in which the federated server and clients from different domains work together to train a global classification model. Among them, unlabeled data are used on the client side, and labeled data are used on the server side. The experimental results derived from a public dataset show that the accuracy of the proposed approach can reach 97.81%, and the accuracy gap between the federated learning approach and the centralized training method is minimal.

Blockchain for medical collaboration: A federated learning-based approach for multi-class respiratory disease classification

The scarcity and diversity of medical data have made it challenging to build an accurate global classification model in the healthcare sector. The prime reason is privacy concerns and legal obstacles which limit data-sharing scope among institutions in healthcare. On the other hand, data from a single source is hardly sufficient to develop a universal diagnosis model. While federated learning is a potential solution to privacy and data diversity concerns (allows distributed model training), an apt aggregation process for multi-class and heterogeneous medical data is still at the outset. This study aims to propose a federated learning mechanism that can effectively learn from multi-class and heterogeneous respiratory medical data. The proposed system trains and aggregates the local model by leveraging blockchain technology, ensuring privacy. While aggregating the local models, we introduced the weight manipulation technique that, unlike any other studies, uses the local model test accuracy as the principal parameter. The resulting metric scores show that learning from diverse and heterogeneous​ data, the performance of the proposed federated model is analogous to a single-source model (learning from single source data). Using the novel aggregation technique, the highest testing accuracy of 88.10% has been achieved for five classes, compared to the less complex single source model, which achieved 88.60% testing accuracy. A similar trend has been observed for models with three and four classes. For developing better synergy among organizations, this study introduces an incentive mechanism for the contributing institution while the blockchain stores the records to make the system transparent and trustworthy. The proposed mechanism has been implemented using a web system, which demonstrates how the weight manipulation technique can effectively learn from heterogeneous and multi-sourced data while preserving privacy.

Global ECG Classification by Self-Operational Neural Networks With Feature Injection.

Global (inter-patient) ECG classification for arrhythmia detection over Electrocardiogram (ECG) signal is a challenging task for both humans and machines. Automating this process with utmost accuracy is, therefore, highly desirable due to the advent of wearable ECG sensors. However, even with numerous deep learning approaches proposed recently, there is still a notable gap in the performance of global and patient-specific ECG classification performance. In this study, we propose a novel approach for inter-patient ECG classification using a compact 1D Self-ONN by exploiting morphological and timing information in heart cycles. We used 1D Self-ONN layers to automatically learn morphological representations from ECG data, enabling us to capture the shape of the ECG waveform around the R peaks. We further inject temporal features based on RR interval for timing characterization. The classification layers can thus benefit from both temporal and learned features for the final arrhythmia classification. Using the MIT-BIH arrhythmia benchmark database, the proposed method achieves the highest classification performance ever achieved, i.e., 99.21% precision, 99.10% recall, and 99.15% F1-score for normal (N) segments; 82.19% precision, 82.50% recall, and 82.34% F1-score for the supra-ventricular ectopic beat (SVEBs); and finally, 94.41% precision, 96.10% recall, and 95.2% F1-score for the ventricular-ectopic beats (VEBs). As a pioneer application, the results show that compact and shallow 1D Self-ONNs with the feature injection can surpass all state-of-the-art deep models with a significant margin and with minimal computational complexity. This study has demonstrated that using a compact and superior network model, a global ECG classification can still be achieved with an elegant performance level even when no patient-specific information is used.

High-Confidence Sample Generation Technology and Application for Global Land-Cover Classification

Deep learning technology has become one of the most important technologies in remote sensing land classification applications. Its powerful sample-learning and information-mining abilities promote the continuous improvement of classification accuracy. A large volume of high-quality and representative sample data is the premise for the successful application of deep learning technology. Conventional methods of obtaining samples through manual delineation or surface surveys require a great deal of manpower and material resources. Therefore, the inability to obtain sufficient and widely representative high-quality samples is one of the key factors limiting the application of deep learning technology. In this study, the method of generating sample data obtains high-confidence classification results from a variety of existing high-quality classification products as deep learning samples, which are then used to support the application of deep learning technology for land-cover classification. When the three global land-cover classification products, FROM-GLC-2015, GLC_FCS30-2015, and GlobeLand30, have the same type of discrimination, the sample is considered a high-confidence sample. Based on this, a large volume of sample data widely distributed around the world was obtained. Using the extracted samples, a random forest classifier was trained using multiple types of information from the Landsat data, and land-cover classification was achieved. Application experiments were conducted in several typical regions, and the classification results were verified. The results showed that the classification accuracy of random forests under the support of samples generated using the sample extraction method proposed in this article was considerably higher than that of the three land-cover classification products.

COVID-19 Classification from X-Ray Images: An Approach to Implement Federated Learning on Decentralized Dataset

The COVID-19 pandemic has devastated our daily lives, leaving horrific repercussions in its aftermath. Due to its rapid spread, it was quite difficult for medical personnel to diagnose it in such a big quantity. Patients who test positive for Covid-19 are diagnosed via a nasal PCR test. In comparison, polymerase chain reaction (PCR) findings take a few hours to a few days. The PCR test is expensive, although the government may bear expenses in certain places. Furthermore, subsets of the population resist invasive testing like swabs. Therefore, chest X-rays or Computerized Vomography (CT) scans are preferred in most cases, and more importantly, they are non-invasive, inexpensive, and provide a faster response time. Recent advances in Artificial Intelligence (AI), in combination with state-of-the-art methods, have allowed for the diagnosis of COVID-19 using chest x-rays. This article proposes a method for classifying COVID-19 as positive or negative on a decentralized dataset that is based on the Federated learning scheme. In order to build a progressive global COVID-19 classification model, two edge devices are employed to train the model on their respective localized dataset, and a 3-layered custom Convolutional Neural Network (CNN) model is used in the process of training the model, which can be deployed from the server. These two edge devices then communicate their learned parameter and weight to the server, where it aggregates and updates the global model. The proposed model is trained using an image dataset that can be found on Kaggle. There are more than 13,000 X-ray images in Kaggle Database collection, from that collection 9000 images of Normal and COVID-19 positive images are used. Each edge node possesses a different number of images; edge node 1 has 3200 images, while edge node 2 has 5800. There is no association between the datasets of the various nodes that are included in the network. By doing it in this manner, each of the nodes will have access to a separate image collection that has no correlation with each other. The diagnosis of COVID-19 has become considerably more efficient with the installation of the suggested algorithm and dataset, and the findings that we have obtained are quite encouraging.