Online Datasets Research Articles

Traffic Prediction using Machine Learning

The traffic is one of the major issues faced by people in almost every city. Predicting the traffic has always been very challenging for transportation planning as well as the city manager. The growth of population and usage of vehicles has increased the need for a reliable traffic prediction system. The system should reduce congestion, avoid accidents, and optimize the traffic flow that enhance road safety. The use of machine learning algorithms would be more suitable in handling the traffic and maintaining the flow of vehicles. The paper focuses on the work related to handling the traffic using machine learning principles such as LSTM and Random Forest (RF) algorithm. The advanced online dataset for traffic forecasts is used. The system is tested to have improved accuracy with the help of feature engineering. The basic dataset had the following fields: Vehicle Id, Time, Date, Junction Id are the primary and significant parameters considered to anticipate the traffic at each zone. With this we have added the day and weekend component to enhance our result.

Age, gender and handedness prediction using handwritten text: A comprehensive survey

Handwriting recognition is widely acknowledged as one of the most challenging tasks in pattern recognition and machine learning. This study explores the intriguing field of age, gender and handedness prediction through handwriting analysis by offering valuable insights into its potential applications in forensics, psychology and education. A comprehensive survey has been conducted encompassing an introduction, motivational aspects, background information, sources of data, analysis schemes, survey protocols, reported findings and methodologies used for predicting age, gender and handedness in both Indic and non-Indic scripts. The investigation highlights research gaps and concludes with an in-depth analysis of unresolved issues accompanied by a roadmap for future advancements in this domain. The survey focuses on a systematic examination of eight Indic scripts (Assamese, Bangla, Devanagari, Gurumukhi, Kannada, Malayalam, Tamil and Telugu) and six non-Indic scripts (Arabic, Chinese, Japanese, Persian, Roman and Thai) and it can be concluded that non-Indic scripts attain more accuracy in comparison with Indic scripts. Furthermore, the study mostly focuses on providing a catalog of publicly accessible online datasets featuring diverse handwriting samples from various scripting languages by giving a roadmap for further research in this area.

Degradation of AZGP1 suppresses the progression of breast cancer cells via TRIM25.

Alpha-2-glycoprotein 1, zinc-binding (AZGP1) is a secreted protein, which has been shown to be a potential biomarker of cancer progression; however, its roles in breast cancer are still unclear. Currently, we analyzed the online datasets and found that AZGP1 was highly expressed in breast cancer tissues and its expression was negatively correlated with the survival of breast cancer patients. Functional experiments through AZGP1 knockdown revealed that AZGP1 could promote the proliferation, migration, and invasion ability of breast cancer cells. In vivo experiments obtained a consistent result. Mechanistically, it was found that AZGP1 interacted with tripartite motif-containing protein 25 (TRIM25), which subsequently promoted AZGP1 degradation through facilitating the ubiquitination. Furthermore, overexpression of TRIM25 partially reversed the promoting effects of AZGP1 overexpression on breast cancer progression. Therefore, this study indicates that AZGP1 might be a potential therapeutic target for breast cancer treatment.

SGMM: Stochastic Approximation to Generalized Method of Moments

Abstract We introduce a new class of algorithms, stochastic generalized method of moments (SGMM), for estimation and inference on (overidentified) moment restriction models. Our SGMM is a novel stochastic approximation alternative to the popular Hansen (1982) (offline) GMM, and offers fast and scalable implementation with the ability to handle streaming datasets in real time. We establish the almost sure convergence, and the (functional) central limit theorem for the inefficient online 2SLS and the efficient SGMM. Moreover, we propose online versions of the Durbin–Wu–Hausman and Sargan–Hansen tests that can be seamlessly integrated within the SGMM framework. Extensive Monte Carlo simulations show that as the sample size increases, the SGMM matches the standard (offline) GMM in terms of estimation accuracy and gains over computational efficiency, indicating its practical value for both large-scale and online datasets. We demonstrate the efficacy of our approach by a proof of concept using two well-known empirical examples with large sample sizes.

CLASSIFICATION OF POTATO LEAF DISEASES USING CONVOLUTIONAL NEURAL NETWORK

Potatoes are an agricultural product that has the fourth highest content of wheat flour after corn, wheat, and rice. Although potatoes play a critical role in agriculture, this crop is susceptible to various diseases and pests. There are several potato leaf diseases that are not yet known to farmers. Dry spot potato leaf disease (late blight) and late blight. If not treated, this disease on potato leaves will spread to the stem and reduce crop yields, causing crop failure. By using technology in the form of digital image processing, this problem can be overcome. This research proposes an appropriate method for detecting disease in potato leaves. Classification will be carried out in three classes, namel, Early Blight, Healthy and Late Blight using the Deep Learning method of Convolutional Neural Network (CNN). The data used comes from an online dataset via the kaggle.com page with the file name Potato Disease Leaf Dataset (PLD) totaling 3251 training datasets which are then divided into training, testing, and validation. The processes carried out are image pre-processing, image augmentation, then image processing using a Convolutional Neural Network (CNN). In the classification process using the CNN method with RMSprop optimizer, the accuracy was 97.53% with a loss value of 0.1096.

PTPRC Inhibits Ferroptosis of Osteosarcoma Cells via Blocking TFEB/FTH1 Signaling.

Protein tyrosine phosphatase receptor type C (PTPRC) is reported to function as an oncogenic role in various cancer. However, the studies on the roles of PTPRC in osteosarcoma (OS) are limited. This study aimed to explore the potentials of PTPRC in OS. mRNA levels were detected by reverse transcription-quantitative polymerase chain reaction (RT-qPCR). Protein expression was detected by western blot. Lysosome biogenesis was determined using immunofluorescence. The binding sites of transcription factor EB (TFEB) on the promoter of ferritin heavy chain 1 (FTH1) were predicted by the online dataset JASPAR and confirmed by luciferase and chromatin immunoprecipitation (ChIP) assays. Cell death was determined using propidium iodide (PI) and TdT-mediated dUTP nick-end labeling (TUNEL) staining. The results showed that PTPRC was significantly overexpressed in OS tissues and cells. PTPRC knockdown promoted the phosphorylation and nuclear translocation of TFEB. Moreover, PTPRC knockdown markedly promoted lysosome biogenesis and the accumulation of ferrous ion (Fe2+), whereas decreased the release of glutathione (GSH). Besides, PTPRC knockdown significantly promoted autophagy and downregulated mRNA expression of FTH1 and ferritin light chain (FTL). Additionally, TFEB transcriptionally inactivated FTH1. PTPRC knockdown significantly promoted the ferroptosis of OS cells, which was markedly alleviated by TFEB shRNA. Taken together, PTPRC knockdown-mediated TFEB phosphorylation and translocation dramatically promoted lysosome biogenesis, ferritinophagy, as well as the ferroptosis of OS cells via regulating FTH1/FTL signaling. Therefore, PTPRC/TFEB/FTH1 signaling may be a potential target for OS.

DNMT1-mediated regulating on FBXO32 promotes the progression of glioma cells through the regulation of SKP1 activity.

Glioma, a prevalent and serious form of brain cancer, is associated with dysregulation of DNA methylation, where DNA methyltransferase-1 (DNMT1) plays a significant role in glioma progression. However, the involvement of F-box protein 32 (FBXO32) in glioma and its regulation by DNMT1-mediated methylation remain poorly understood. In this study, we investigated FBXO32 expression in glioma cells with high DNMT1 expression using the online dataset and correlated it with patient survival. Then impact of elevated FBXO32 expression on cell proliferation, migration, and invasion was evaluated, along with the examination of EMT-related proteins. Furthermore, a xenograft model established by injecting glioma cells stably transfected with FBXO32 was used to evaluate tumor growth, volume, and weight. The ChIP assay was employed to study the interaction between DNMT1 and the FBXO32 promoter, revealing that DNMT1 negatively correlated with FBXO32 expression in glioma cells and promoted FBXO32 promoter methylation. Moreover, we investigated the interaction between FBXO32 and SKP1 using Co-IP and GST pulldown assays, discovering that FBXO32 acts as an E3 ubiquitin ligase and promotes SKP1 ubiquitination, leading to its degradation. Interestingly, our findings demonstrated that high FBXO32 expression was associated with improved overall survival in glioma patients. Knockdown of DNMT1 in glioma cells increased FBXO32 expression and suppressed malignant phenotypes, suggesting that FBXO32 functions as a tumor suppressor in glioma. In conclusion, this study reveals a novel regulatory mechanism involving DNMT1-mediated FBXO32 expression in glioma cells, where FBXO32 acts as an E3 ubiquitin ligase to degrade SKP1 via ubiquitination. This FBXO32-mediated regulation of SKP1 activity contributes to the progression of glioma cells. These findings provide important insights into the molecular mechanisms underlying glioma progression and may hold promise for the development of targeted therapies for glioma patients.

Pretreatment radiomic biomarker for immunotherapy responder prediction in stage IB–IV NSCLC (LCDigital-IO Study): a multicenter retrospective study

BackgroundThe predictive efficacy of current biomarker of immune checkpoint inhibitors (ICIs) is not sufficient. This study investigated the causality between radiomic biomarkers and immunotherapy response status in patients with stage...

DLK1 overexpression improves sepsis-induced cardiac dysfunction and fibrosis in mice through the TGF-β1/Smad3 signaling pathway and MMPs.

Sepsis is a serious inflammatory disease caused by bacterial infection. Cardiovascular dysfunction and remodeling are serious complications of sepsis, which can significantly affect sepsis patients' mortality. Delta-like homologue 1 (DLK1) has been reported could inhibit cardiac myofibroblast differentiation. However, the function of DLK1 in sepsis is unknown. In the present study, the DLK1 expression was first identified based on the online dataset GSE79962 analysis and cecal ligation and puncture (CLP)-induced sepsis mouse model. DLK1 expression was significantly reduced in septic heart tissues. In septic mouse heart, CLP operation decreased the fractional shortening (EF) (%) and ejection fraction (FS) (%) and caused significant edema, disordered myofilament arrangement, and degradation and necrosis in myocardial cells; CLP operation also increased collagen deposition and elevated the protein levels of fibrotic markers (α-SMA and F-actin). DLK1 overexpression in septic mice could effectively increase EF (%) and FS (%), attenuate CLP-caused ECM degradation and deposition and partially inhibit the CLP-induced TGF-β1/Smad signaling activation. In conclusion, DLK1 expression was poorly expressed in the CLP-induced septic mouse heart. DLK1 overexpression partially alleviated sepsis-induced cardiac dysfunction and fibrosis, with the involvement of the TGF-β1/Smad3 signaling pathway and MMPs.

Variations of Middle Cerebral Artery Hemodynamics Due to Aneurysm Clipping Surgery

Abstract Cerebral aneurysms are potentially life-threatening cerebrovascular conditions where a weakened blood vessel in the brain bulges or protrudes over time. The most common way to treat aneurysms is surgical clipping, an approach where blood flow to the aneurysm is blocked by a permanently placed clip on the artery. However, not all aneurysms are identical; thus, there has been a need for patient-specific treatment options, where each aneurysm is treated based on its individual characteristics. Computational fluid dynamics (CFD) modeling can offer insights to predict how different treatment procedures will affect cerebral hemodynamics. In that regard, the goal of this pilot study was to investigate the flow characteristics and hemodynamic parameters in cerebral arteries before and after neurosurgical clipping. For this purpose, two patient-specific cerebral artery geometries with at least one aneurysm at the middle cerebral artery bifurcation were selected from an online dataset. A companion postclipping model was created for each geometry by removing the aneurysm from the original geometry. Tetrahedral mesh elements were then generated and CFD simulations were conducted to compare the blood velocity profile, secondary flow, flow streamline, and wall shear stress in the computational models with and without aneurysm. Results showed that the clipping treatment led to changes in the velocity profiles, secondary flow structures, and wall shear stress in the middle cerebral artery. In conclusion, our results suggest that CFD modeling can assist in predicting hemodynamic parameters prior to treatment, thus facilitating more tailored planning for each patient’s treatment.

Copine 1 predicts poor clinical outcomes by promoting M2 macrophage activation in ovarian cancer.

Copine 1 (CPNE1), a membrane-binding protein, influences the prognosis of various cancers. According to cBioPortal, CPNE1 amplification is a prevalent genetic mutation in ovarian cancer but with unknown oncogenic mechanism. This study analysed the CPNE1 expression in ovarian cancer using online datasets, as validated by immunohistochemistry (IHC), quantitative polymerase chain reaction (qPCR) and western blotting. Concurrently, the prognostic value of CPNE1 was accessed. Cell Counting Kit-8, colony formation, transwells and xenograft experiments were performed to evaluate the functions of CPNE1 during ovarian cancer carcinogenesis. CPNE1 and its related genes were analysed by g:Profiler and Tumour Immune Estimation Resource. Furthermore, human monocytic THP-1 cells were co-cultured with ES2 cells to investigate the effect of CPNE1 on macrophage polarization. The results of bioinformatic analysis, IHC, qPCR and western blotting indicated a higher CPNE1 in ovarian cancer. CPNE1 overexpression demonstrated an association with a poor prognosis of ovarian cancer. Functionally, CPNE1 overexpression increased ES2 and SKOV3 cell proliferation, invasion and migration in vitro and promoted ovarian tumour xenograft growth in vivo, while CPNE1 knockdown led to opposite effects. Additionally, CPNE1 expression demonstrated an association with immune cell infiltration in ovarian cancer, especially macrophage. CPNE1 promoted protumour M2 macrophage polarization by upregulating cluster of differentiation 163 (CD163), CD206 and interleukin-10. Our study revealed that CPNE1 mediated M2 macrophage polarization and provided a therapeutic target for ovarian cancer.

Detecting anomalies in fetal electrocardiogram records using deep learning models

In order to assess the fetus health and make timely decisions throughout pregnancy, Fetal Electrocardiography (FECG) monitoring is essential. Huge datasets for electrocardiograms are freely accessible from Physionet ATM Dataset1- Abdominal and Direct Fetal ECG Database (adfecgdb), Dataset2- Fetal ECG Synthetic Database (fecgsyndb), Dataset3- Non-Invasive Fetal ECG Database(nifecgdb). In this study, we strive to categorize normal and abnormal (Atrial fibrillation) FECG from three online dataset which contains FECG recordings as major details. Deep learning models like Transfer Learning (TL) and Convolutional Neural Networks (CNN) are being investigated. The composite abdominal signal and the FECG are separated using a wavelet transform approach. The best model for categorizing the parameters of the FECG is determined through a comparative analysis and performance is improved using Continuous Wavelet Transform (CWT). The accuracy of the CNN-based technique is found to be 98.59%, whereas the accuracy of the transfer learning model is 99.01% for FECG classification. The computation of metric parameters for all the datasets is done. The classification of normal and abnormal (Atrial fibrillation) is best performed in TL model compared to CNN. Real-time data analysis is done for PQRST plotting and comparative study is done using Net Reclassification Improvement (NRI) and obtained NRI = 13%, z static 0f 3.7641, p-Value of 0.00016721. Acute Myocardial Infraction (AMI) identification is done based on ST segment of Maternal ECG (MECG) images to analyze the heart attack risk. The proposed work can be utilized to track FECG waveforms in real-time for wearable technology because of its end-to-end properties and expandable intrinsic for diagnosing multi-lead heart disorders.

An effective disease diagnostic model related to pyroptosis in ischemic cardiomyopathy.

Pyroptosis is involved in ischemic cardiomyopathy (ICM). The study aimed to investigate the pyroptosis-related genes and clarify their diagnostic value in ICM. The bioinformatics method identified the differential pyroptosis genes between the normal control and ICM samples from online datasets. Then, protein-protein interaction (PPI) and function analysis were carried out to explore the function of these genes. Following, subtype analysis was performed using ConsensusClusterPlus, functions, immune score, stromal score, immune cell proportion and human leukocyte antigen (HLA) genes between subtypes were investigated. Moreover, optimal pyroptosis genes were selected using the least absolute shrinkage and selection operator (LASSO) analysis to construct a diagnostic model and evaluate its effectiveness using receiver operator characteristic (ROC) analysis. Twenty-one differential expressed pyroptosis genes were identified, and these genes were related to immune and pyroptosis. Subtype analysis identified two obvious subtypes: sub-1 and sub-2. And LASSO identified 13 optimal genes used to construct the diagnostic model. The diagnostic model in ICM diagnosis with the area under ROC (AUC) was 0.965. Our results suggested that pyroptosis was tightly associated with ICM.

An Analysis of JADE2 in Non-Small Cell Lung Cancer (NSCLC).

The JADE family comprises three members encoded by individual genes and roles for these proteins have been identified in chromatin remodeling, cell cycle progression, cell regeneration and the DNA damage response. JADE family members, and in particular JADE2 have not been studied in any great detail in cancer. Using a series of standard biological and bioinformatics approaches we investigated JADE2 expression in surgically resected non-small cell lung cancer (NSCLC) for both mRNA and protein to examine for correlations between JADE2 expression and overall survival. Additional correlations were identified using bioinformatic analyses on multiple online datasets. Our analysis demonstrates that JADE2 expression is significantly altered in NSCLC. High expression of JADE2 is associated with a better 5-year overall survival. Links between JADE2 mRNA expression and a number of mutated genes were identified, and associations between JADE2 expression and tumor mutational burden and immune cell infiltration were explored. Potential new drugs that can target JADE2 were identified. The results of this biomarker-driven study suggest that JADE2 may have potential clinical utility in the diagnosis, prognosis and stratification of patients into various therapeutically targetable options.

Construction of a novel circRNA-miRNA-ferroptosis related mRNA network in ischemic stroke

Molecule alterations are important to explore the pathological mechanism of ischemic stroke (IS). Ferroptosis, a newly recognized type of regulated cell death, is related to IS. Identification of the interactions between circular RNA (circRNA), microRNA (miRNA) and ferroptosis related mRNA may be useful to understand the molecular mechanism of IS. The circRNA, miRNA and mRNA transcriptome data in IS, downloaded from the Gene Expression Omnibus (GEO) database, was used for differential expression analysis. Ferroptosis related mRNAs were identified from the FerrDb database, followed by construction of circRNA-miRNA-ferroptosis related mRNA network. Enrichment and protein–protein interaction analysis of mRNAs in circRNA-miRNA-mRNA network was performed, followed by expression validation by reverse transcriptase polymerase chain reaction and online dataset. A total of 694, 41 and 104 differentially expressed circRNAs, miRNAs and mRNAs were respectively identified in IS. Among which, dual specificity phosphatase 1 (DUSP1), nuclear receptor coactivator 4 (NCOA4) and solute carrier family 2 member 3 (SLC2A3) were the only three up-regulated ferroptosis related mRNAs. Moreover, DUSP1, NCOA4 and SLC2A3 were significantly up-regulated in IS after 3, 5 and 24 h of the attack. Based on these three ferroptosis related mRNAs, 4 circRNA-miRNA-ferroptosis related mRNA regulatory relationship pairs were identified in IS, including hsa_circ_0071036/hsa_circ_0039365/hsa_circ_0079347/hsa_circ_0008857-hsa-miR-122-5p-DUSP1, hsa_circ_0067717/hsa_circ_0003956/hsa_circ_0013729-hsa-miR-4446-3p-SLC2A3, hsa_circ_0059347/hsa_circ_0001414/hsa_circ_0049637-hsa-miR-885-3p-SLC2A3, and hsa_circ_0005633/hsa_circ_0004479-hsa-miR-4435-NCOA4. In addition, DUSP1 is involved in the signaling pathway of fluid shear stress and atherosclerosis. Relationship of regulatory action between circRNAs, miRNAs and ferroptosis related mRNAs may be associated with the development of IS.

Ordinal Conditional Entropy Displays Reveal Intrinsic Characteristics of the Rosenberg Self-Esteem Scale.

Individual subjects' ratings neither are metric nor have homogeneous meanings, consequently digital- labeled collections of subjects' ratings are intrinsically ordinal and categorical. However, in these situations, the literature privileges the use of measures conceived for numerical data. In this paper, we discuss the exploratory theme of employing conditional entropy to measure degrees of uncertainty in responding to self-rating questions and that of displaying the computed entropies along the ordinal axis for visible pattern recognition. We apply this theme to the study of an online dataset, which contains responses to the Rosenberg Self-Esteem Scale. We report three major findings. First, at the fine scale level, the resultant multiple ordinal-display of response-vs-covariate entropy measures reveals that the subjects on both extreme labels (high self-esteem and low self-esteem) show distinct degrees of uncertainty. Secondly, at the global scale level, in responding to positively posed questions, the degree of uncertainty decreases for increasing levels of self-esteem, while, in responding to negative questions, the degree of uncertainty increases. Thirdly, such entropy-based computed patterns are preserved across age groups. We provide a set of tools developed in R that are ready to implement for the analysis of rating data and for exploring pattern-based knowledge in related research.

Noncoding RNA-Mediated High Expression of PFKFB3 Correlates with Poor Prognosis and Tumor Immune Infiltration of Lung Adenocarcinoma.

There is growing evidence showing that 6-phosphofructo-2-kinase (PFKFB3) plays crucial roles in different types of human cancers, including LUAD; however, the specific mechanism by which PFKFB3 plays a role in LUAD remains unclear. We investigated the expression of PFKFB3 and explored the underlying mechanism as well as the correlation with immune markers using several online datasets, such as Tumor Immune Estimate Resource (TIMER), UALCAN, and the Cancer Genome Atlas (TCGA) databases, miRWalk, Targetscan, MiRDB and starBase database. Western blot and immunohistochemistry analysis were performed to verify the corresponding outcomes. It was shown that the mRNA expression of PFKFB3 was lower in LUAD than in the normal tissues, while its protein expression was not consistent with the mRNA level. The expression of PFKFB3 was correlated with clinicopathological parameters and several signaling pathways. The potential long chain (lnc)RNA/microRNA/PFKFB3 axis and the possible mechanism by which tumor progression in LUAD is promoted was predicted. We obtained the LINC01798/LINC02086/AP000845.1/HAGLR-miR-17-5p-PFKFB3 axis after comprehensive analyses of expression, correlation, and survival. Moreover, the expression of PFKFB3 was positively correlated with immune cells and immune checkpoint expression, including PD-1, PD-L1 and CTLA-4. The present study demonstrated that noncoding RNAs mediated the upregulation of PFKFB3 and was associated with a poor prognosis and immune tumor infiltration in LUAD.

Onion supplementation and health metabolic parameters: A systematic review and meta-analysis of randomized controlled trials

Functional foods, such as onions, have been the center of many recent investigations. In this systematic-review and meta-analysis, we aimed to gather up the existing information with regard to the impact of onion supplementation on anthropometric measurements/indices, lipid profile, indices of glycemic control and hepatic health, systolic and diastolic blood pressures (SBP and DBP), and adiponectin and leptin. All major online datasets (PubMed, Web of Science, Cochrane, and Scopus) were thoroughly searched from inception up to October 2022. Relevant randomized controlled trials (RCTs) were obtained using the eligibility criteria. Weighted mean differences (WMDs) were calculated and reported. Statistical significance was set as p-values <0.05. Among all the retrieved data, 14 RCTs were eligible to be included. The results of the crude analysis showed that onion supplementation significantly improved body fat percentage (BFP), low-density lipoprotein-cholesterol (LDL-c), total cholesterol (TC), high-density lipoprotein-cholesterol (HDL-c), systolic blood pressure, adiponectin, and aspartate aminotransferase (AST). Subgroup analysis revealed that interventions lasting more than 12 weeks can significantly alter weight, waist circumference (WC), body mass index (BMI), BFP, LDL-c, TC, SBP, and DBP. Moreover, the intake of dosages of >300mg/day of onion supplementation could significantly improve weight, WC, BMI, BFP, LDL-c, HDL-C, TC, AST, ALT, SBP and DBP. It seems that the intake of onion supplementation can improve health metabolic parameters. We observed that with either longer follow-up periods or higher dosages of onion supplementation, improvements in cardio-metabolic parameters could be expected.

Classification of Pneumonia, Tuberculosis, and COVID-19 on Computed Tomography Images using Deep Learning

The accurate diagnosis of pneumonia, tuberculosis, and COVID-19 using computed tomography (CT) images is critical for radiologists. Artificial intelligence (AI) has been introduced as a tool to aid in rapid diagnosis. In this study, we evaluated 4 deep learning models, including AlexNet, GoogleNet, ResNet, and deep convolutional neural network (DCNN), to classify CT images of tuberculosis, pneumonia, and COVID-19. We collected 2,134 normal images, 943 images of tuberculosis, 2,041 images of pneumonia, and 3,917 images of COVID-19 from online datasets. To assess the efficiency of the models, we measured their image classification performance such as accuracy, F1 score, and area under the curve. Our performance evaluation indicated that ResNet was the highest-performing model, with the best accuracy, F1 score, and area under the curve (0.966, 0.931, 0.954, respectively). The second-best performing model was DCNN, while AlexNet and GoogleNet had the next-best performance, respectively. The deep learning models exhibit a capability that could be viewed as a substitute for predicting lung diseases and could be employed to support radiologists in CT image screening. HIGHLIGHTS The four deep learning models including AlexNet, GoogleNet, ResNet, and DCNN can classified for 4 classes (tuberculosis, pneumonia, COVID-19, and normal) The AUC indicates the model's ability to distinguish between positive and negative images, ResNet had the highest AUC for normal, pneumonia, and COVID-19, while AlexNet was highest for tuberculosis The ResNet model performed the best in terms of accuracy of model prediction, correctly predicting the labels for all 4 classes of input data (tuberculosis, pneumonia, COVID-19, and normal) GRAPHICAL ABSTRACT

Exploring Language Variation in Internet Buzzwords: A Case Study of the Phrase “Officially Diagnosed as XX”

Internet buzzwords, characterized by their interactivity and permeability, serve as indicators of the shifting emotional landscapes and emotional appeals of netizens within distinct temporal contexts. However, these buzzwords remain far from stagnant, continually undergoing linguistic variations influenced by the psychological dispositions of users and the ever-shifting environmental backdrop. In this case study, a comprehensive exploration of linguistic variation within internet buzzwords is undertaken, focusing intently on the dynamic phrase "officially diagnosed as XX" and its profound reflection of prevailing social mentalities and linguistic motivations. Guided by the conceptual framework of eco-linguistics, which offers a lens for comprehending the economic underpinnings of language and rationalizing the phenomena of internet buzzwords, this study delves into an intricate analysis. By meticulously dissecting online datasets and user commentary, the study unveils the multifaceted employment of "officially diagnosed as XX" as an instrument to articulate an array of emotions and cognitive states, ranging from humor to frustration and even self-deprecation. Through the prism of language evolution in the digital era, the study engages in a scholarly discourse on the intricate phenomenon of linguistic variation within the realm of internet discourse. Ultimately, this research not only illuminates the intricate dynamics between language, society, and technology in the contemporary age but also advances our comprehension of the profound interplay between language, emotion, and human communication within the digital realm.