Sensitivity And Specificity Research Articles

Acoustic feature-based emotion recognition and curing using ensemble learning and CNN

Emotion recognition and understanding plays a crucial role in various domains, including healthcare, human-computer interaction, and mental well-being. In this context, this paper proposes a methodology for recognizing and curing emotions using acoustic features and machine learning algorithms. The approach involves extracting acoustic features from the signals using diverse signal processing techniques. These features are then utilized as inputs for machine learning and deep learning algorithms, including the Random Forest classifier, XG Boost classifier, Convolutional Neural Network (CNN), and an ensemble algorithm. The ensemble algorithm combines Random Forest and XG Boost as base classifiers, with the Naïve Bayes algorithm serving as the meta classifier. We also propose a novel model that generates personalized curing strategies for individuals based on emotion recognition, so they can keep their emotional state positive. With the help of an ensemble learning model the proposed model achieved an emotion recognition accuracy of 92 % by combining three publicly available datasets containing emotional speech recordings. In the neutral and positive emotion classifications, the Receiver Operating Characteristic curve (ROC) had a 98 % accuracy rate while negative emotion classifications had a 91 % true positive rate. The effectiveness of the proposed curing methodology model has also been demonstrated by conducting experiments on a group of individuals and comparing the results with a state-of-the-art Generative Pre-Trained Transformer-3 (GPT-3) and ChatGPT, it was inferred that 89.35 % of the test group preferred the responses of the proposed curing model, over the GPT models The results of our experiments show that our proposed methodology can significantly boost the emotional state of an individual, thereby highlighting its potential for use in clinical settings.

Classifying Anemia Diseases based on VGG-16 and CBAM Attention Mechanism Models

Anemia is a major public health concern and has a significant impact on women and children worldwide. This condition is caused by a lack of sufficient Red Blood Cells (RBCs). Traditionally, anemia diagnosis has relied on invasive techniques that require blood samples, leading to pain and discomfort. This study explores deep learning techniques for automating and enhancing anemia detection accuracy using the Blood Cell Count and Detection (BCCD) dataset. We employ the VGG16 convolutional neural network architecture augmented with the Convolutional Block Attention Module (CBAM) to boost feature representation and performance. The BCCD dataset, consisting of 364 images with 4888 labeled blood cells, was used for training and evaluation. Our enhanced VGG16 model achieved accuracy for RBCs, WBCs, and platelets with values of 0.84, 0.93, and 0.92, respectively, effectively identifying various blood cell types and detecting anemia. Precision-recall analysis and confusion matrix metrics confirmed the robustness of the model, with high precision and recall rates and minimal false positives and negatives. These results suggest that advanced deep learning models with attention mechanisms, such as CBAM, can significantly improve medical diagnostics by providing reliable, efficient, and accurate early disease detection tools. Future development will be directed towards fine-tuning and validating the proposed model on other medical imaging datasets for clinical applications.

Predicting rock art sites in the Pajeú watershed, Brazil

This paper presents an Archaeological Predictive Model (APM) to predict rock art archaeological sites in the Pajeú Watershed, a semiarid region in Pernambuco, Brazil. The model uses Machine Learning (ML) algorithms and re-sampling techniques to account for the unbalanced data set of rock art sites and test different inductive methods for predicting site location. The results show a satisfactory statistical evaluation, with high true positive rates with all ML algorithms and resampling techniques used, indicating a high potential for predicting rock art site locations. The predictive maps generated from the model output, show that certain features, such as aspect, elevation and the distance to different lithologies, are particularly important. The overall model's performance could be corroborated with a test in another semi-arid region, next to the Pajeú watershed, where areas with high favorability of finding rock art sites are predicted near to already known archaeological sites.

Self-prompting semantic segmentation of bridge point cloud data using a large computer vision model

Semantic segmentation of bridge Point Cloud Data (PCD) is an intermediate process required for the tasks such as deformation detection and digital twin. However, existing methods either require a substantial amount of training data or exhibit limited generalization ability. To address these issues, this paper presents an unsupervised framework for semantic segmentation of bridge PCD. A visible point rendering method is first employed to bridge the modal gap between 2D and 3D, and then a self-prompting segmentation method based on a large computer vision model is introduced to achieve instance segmentation. Experiment results on the real-world reinforced concrete bridge dataset and suspension bridge dataset showed the proposed method achieved the outstanding performance on all overall evaluation metrics of overall accuracy (98.31 % and 98.10 %), mean precision (97.67 % and 93.96 %), mean recall rate (97.50 % and 97.51 %) and mean F1 score (97.46 % and 95.55 %). The comparisons with existing methods demonstrate that without the need of training data, our method can achieve competitive or even superior accuracy to learning-based methods.

Design and deployment of zero-trust SMPC algorithm to enhance financial cybersecurity in small and medium scale supply chains in the United States

This study designs and deploys zero-trust secure multiparty computation (SMPC) algorithms to enhance financial cybersecurity in small and medium-sized enterprises (SMEs) within the U.S. supply chain. Utilizing TensorFlow for machine learning, Apache Kafka for real-time data processing, and SMPC protocols, the proposed solution aims to provide robust, scalable, and economically viable cybersecurity measures. The research involved developing advanced machine learning-based zero-trust algorithms using TensorFlow, integrating SMPC protocols for secure data computation, and utilizing Apache Kafka for real-time data processing. The algorithms were tested and validated in both simulated and real-world SME environments to evaluate their effectiveness. The implementation of zero-trust SMPC algorithms led to significant improvements in various cybersecurity metrics. The true positive rate (TPR) increased from 85% to 98%, and the false positive rate (FPR) decreased from 5% to 1%. Average incident response time was reduced from 4 hours to 1 hour, and the average cost per incident decreased by 80%, with data loss per incident reduced by 90%. Compliance with GDPR and CCPA standards improved by 35.71% and 38.46%, respectively. User satisfaction increased by 41.67%, and system availability improved from 95% to 99%, with network latency decreasing by 60%. The results demonstrate that zero-trust SMPC algorithms significantly enhance financial cybersecurity for SMEs, reducing security incidents and financial impacts, improving regulatory compliance, and increasing user satisfaction and system performance. These advancements are crucial for strengthening the resilience and stability of the U.S. supply chain, supporting economic growth.

Curvature analysis of CI electrode arrays: a novel approach to categorize perimodiolar positions without anatomical landmarks.

Perimodiolar electrode arrays may be positioned regular, over-inserted or under-inserted into the cochlea depending on the cochlear size and shape. The study aimed to examine whether there are differences between these groups in the local curvature along the intracochlear array. Individual curvature variables were developed to categorize the groups and the relationship between the curvature and the angular insertion depth at the electrode tip was analyzed. The curvature along the intracochlear array was measured in the CBCT image of 85 perimodiolar electrodes of a single type. The mean curvature and the ratio of the mean curvature at contacts E14-16 to the mean curvature at E7-8 (bowing ratio) were calculated across the array, and its true positive rate (TPR) and false positive rate (FPR) were calculated to establish optimal threshold values to categorize the groups. 68.2% of the cases were categorized as regular positioned, 22.4% had an over-insertion and 9.4% had an under-insertion. The mean curvature was significantly weaker with under-insertion (< 342°) than with normal insertion depth (≥ 342°). With an over-insertion, the bowing ratio was < 1 and otherwise > 1. Both the mean curvature and bowing ratio were found to have an optimal threshold value with high TPR (= 1.00) and low FPR (≤ 0.06) for categorizing under-insertion and over-insertion, respectively. Curvature analysis is a useful tool to assess if a perimodiolar electrode array has been inserted deep enough into the cochlea. Independent of critical anatomical landmarks, over-inserted arrays and under-inserted arrays could be well categorized by using individual curvature variables. The results need to be validated using additional data sets.

Cross media knowledge information retrieval model based on D-S evidence theory

Cross media knowledge information retrieval provides strong support for information processing and utilization in the information society, but there are problems such as heterogeneity in cross media knowledge information. Therefore, a cross media knowledge information retrieval model using D-S evidence theory is proposed, which involves using approximate calculation methods to improve this theory for information fusion, reducing computational complexity, and using deep networks for fine-grained information retrieval to improve retrieval accuracy. The results showed that the improved theory enhanced computational efficiency by about 27.23 %. The memory usage was <60 %, and the average accuracy of information fusion reached 93.14 %. It also exhibited high recall and low false alarm rates. The cross media knowledge information retrieval model proposed in the study achieved accuracy of 92.64 %, 96.49 %, and 97.46 % on the three datasets used in the experiment, respectively. The study provides an effective, computationally efficient, and highly accurate model for cross media knowledge information retrieval, which is expected to promote research and application in this field. The combination of improved D-S evidence theory and deep networks provides a powerful approach to solving the problem of cross media heterogeneous information retrieval, which has a positive promoting effect on the processing and utilization of information in the information society.

SAD: semi-supervised automatic detection of BOLD activations in high temporal resolution fMRI data.

Despite the prevalent use of the general linear model (GLM) in fMRI data analysis, assuming a pre-defined hemodynamic response function (HRF) for all voxels can lead to reduced reliability and may distort the inferences derived from it. To overcome the necessity of presuming a specific model for the hemodynamic response, we introduce a semi-supervised automatic detection (SAD) method. The proposedSADmethod employs a Bi-LSTM neural network to classify high temporal resolution fMRI data. Network training utilized an fMRI dataset with 75-ms temporal resolution in an iterative scheme. Classification performance was evaluated on a second fMRI dataset from the same participant, collected on a different day. Comparative analysis with the standard GLM approach was conducted to evaluate the cooperativeeffectiveness of the SAD method. The SAD method performed well based on the classification scores: true-positive rate = 0.961, area under the receiver operating curve = 0.998, true-negative rate = 0.99, F1-score = 0.979, False-negative rate = 0.038, false-discovery rate = 0.002, false-positive rate = 0.002 at 75-ms temporal resolution. SAD can detect hemodynamic responses at 75-ms temporal resolution without relying on a specific shape of an HRF. Future work could expand the use cases to include more participants and different fMRI paradigms.

Mangrove species detection using YOLOv5 with RGB imagery from consumer unmanned aerial vehicles (UAVs)

Despite comprising only one per cent of global forests, mangroves provide vital ecological and economic benefits to their ecosystems. Due to its decreasing extent over the past decade, there is a rise in research innovations supporting mangrove conservation. Specifically, consumer-grade Unmanned Aerial Vehicles (UAV) were proven effective as potential remote sensing alternatives to support mangrove research and monitoring in recent studies. As most studies use custom UAV-mounted sensors for mangrove species classification, similar studies using a UAV’s default red–green–blue (RGB) cameras were scarce. This study explores the potential of high-resolution RGB aerial images through state-of-the-art object detection algorithm, YOLOv5 to detect the dominant Rhizophora mangroves in Sarawak, Malaysia. A total of 400 RGB images were equally selected from two study areas and allocated into three datasets, two corresponding to each study area and one combining all images. The annotation process was performed using a previously proposed novel method, assisted by YOLOv5 for a semi-automated annotation process with expert verification. Systematic training experiments were conducted to select an optimal epoch size across models trained with each dataset. The final models produced an average true positive rate of 73.8% and 71.7% for each study site, while the combined dataset model produced an average true positive rate of 73.7%. Overall, this study demonstrated the potential of UAV-based RGB images and deep learning object detection architectures to identify specific mangrove objects, while also highlighting key considerations for similar future research.

Behavioral analysis of electricity consumption characteristics for customer groups using the k-means algorithm

In the fierce competition of the electricity market, how to consolidate and develop customers is particularly important. Aiming to analyze the electricity consumption characteristics of customer groups, this paper used a k-means algorithm and optimized it. The number of clusters was determined by the Davies-Bouldin index (DBI). An improved Harris Hawks optimization (IHHO) algorithm was designed to realize the initial cluster center selection. Based on data such as electricity purchase and average electricity price, electricity customer groups were clustered using the IHHO-k-means algorithm. The IHHO-k-means algorithm achieved the best clustering effect on Iris, Wine, and Glass datasets compared with the traditional k-means and PSO-k-means algorithms. Taking Iris as an example, the optimal value of the IHHO-k-means algorithm was 96.538, with an accuracy rate of 0.932, precision and recall rates of 0.941 and 0.793, respectively, an F-measure of 0.861, and an area under the curve (AUC) value of 0.851. In the customer dataset, the number of clusters determined by DBI was 4. The power customers were divided into four groups with different characteristics of electricity consumption, and their electricity consumption behaviors were analyzed. The results prove the reliability of the IHHO-k-means algorithm in analyzing electricity consumption characteristics of customer groups, and it can be applied in practice.

Environment Aspects and Daily Life-Threatening Risk Prediction for Improving Public Health Using Ensemble Learning Techniques

Increasing work nature in the fastest world need relaxing to maintain public health is important. But the continuous imbalance of work nature in human daily life doesn’t have time to consecrate the health with leads life threatening facts such as work tension, management stress, job professional, family needs, improper periodic work cycle, and soon. By analyzing the daily public life threatening risk prediction based on Feature selection and classification to category the public health to recommend for phycological treatment. By suggesting treatment schedule are important to balance the public health Lifecyle to make stress free life to spent with nature. Most of prevailing techniques analyse the life-threatening issues, but the features are improperly to taken without the mutual relation cause poor accuracy in precision and classifications rate with more false prediction rate. To tackle this issue, to propose an optimized ensemble learning Techniques based on multi scalar support vector machine (MSSVM) with deep scaled XGboost classifier (DSXG-boost) to improve the prediction accuracy. Initially the public life Cycle dataset is collected and to make normalization using Min-max normalization. Then the Public Life Threat Impact Rate (PLTIR) is analysed to marginalize the heath affecting features. Then then stress margin dependencies feature limits are selected with support of MSSVM. The selected features are grouped in cluster margins and classified with deep scaled XG boost algorithm to predict the active and inactive heath margin be categorized by risk threaten class. The proposed system prove the prediction accuracy in higher precision are by selecting mutual dependencies of health affection feature limits and best recall rate to improve the performance. Based on the predicted class, the categorized life threaten risk peoples are recommends to make phycological treatment to protect the public life cycle.

A Comparison of the Alvarado Score and the Raja Isteri Pengiran Anak Saleha Appendicitis (RIPASA) Score in the Diagnosis of Acute Appendicitis: A Prospective Cohort Study.

Background Diagnosing acute appendicitis remains a problem, especially in teenagers with right lower quadrant pain.Imaging studies aid in accurate diagnosis but have limitations such as cost and availability. The Modified Alvarado Scoring System (MASS) is simple and cost-effective with fewer parameters. The Raja Isteri Pengiran Anak Saleha Appendicitisscoring system (RIPASA), designed for Asian populations, includes more parameters. This study compares the effectiveness of RIPASA and Alvarado scores in diagnosing acute appendicitis in a specific clinical setting. Objectives To compare the scoring systems of RIPASA and Alvarado in the diagnosis of acute appendicitis at a tertiary care hospital. Methods Data has been collected from all patients who attended the NRI general hospital emergency department and outpatient wing with acute appendicitis, admitted as inpatients based on clinical history and relevant investigations. Patients satisfying inclusion and exclusion criteria were selected and the basic investigations were done. Summary statistics were done using mean, standard deviation and proportions. Inferential statistics were done by using an independent t-test, kappa statistic, sensitivity and specificity with a 95% confidence interval (CI). All the measurements are done using the statistical package for the social sciences (SPSS) software version 21.0 (IBM Corp., Armonk, NY, USA) and open epidemiological (OpenEpi) software 3.01. A probability (p) <0.05 is considered as statistically significant. Results A total of 110 patients were analyzed for this study with a majority (39%) of them in the 21-30 age group. In our study, females (53%) outnumbered males (47%). Ultrasound findings in our cohort were acute appendicitis (93%), chronic appendicitis (2%) and normal appendix (5%). However, histopathology reported acute appendicitis (75%), chronic appendicitis (9%) and negative/non-specific (15%). The probability of appendicitis as predicted by Alvarado and RIPASA were 40% and 51% respectively. Definitive diagnosis of appendicitis was made in 16.4% with RIPASA whereas only 5.5% with Alvarado. When comparing the Alvarado and RIPASA scores, the sensitivity or true positive rate was higher for RIPASA (73.63%) than for Alvarado (50.55%). Conclusion There was a significant difference between the mean scores in Alvarado and RIPASA inpatients with scores suggestive of appendicitis and no appendicitis. Diagnostic accuracy was higher in RIPASA scoring compared to ALVARDO scoring. There was a significant statistical difference between the two scoring systems. When it comes to diagnosing in low-resource countries the study recommends a combination of Alvarado and RIPASA scoring systems.

Diagnosis of acute hyperglycemia based on data-driven prediction models

Acute hyperglycemia is a common endocrine and metabolic disorder that seriously threatens the health and life of patients. Exploring effective diagnostic methods and treatment strategies for acute hyperglycemia to improve treatment quality and patient satisfaction is currently one of the hotspots and difficulties in medical research. This article introduced a method for diagnosing acute hyperglycemia based on data-driven prediction models. In the experiment, clinical data from 1000 patients with acute hyperglycemia were collected. Through data cleaning and feature engineering, 10 features related to acute hyperglycemia were selected, including BMI (Body Mass Index), TG (triacylglycerol), HDL-C (High-density lipoprotein cholesterol), etc. The support vector machine (SVM) model was used for training and testing. The experimental results showed that the SVM model can effectively predict the occurrence of acute hyperglycemia, with an average accuracy of 96 %, a recall rate of 84 %, and an F1 value of 89 %. The diagnostic method for acute hyperglycemia based on data-driven prediction models has a certain reference value, which can be used as a clinical auxiliary diagnostic tool to improve the early diagnosis and treatment success rate of acute hyperglycemia patients.

Camouflage detection: Optimization-based computer vision for Alligator sinensis with low detectability in complex wild environments

Alligator sinensis is an extremely rare species that possesses excellent camouflage, allowing it to fit perfectly into its natural environment. The use of camouflage makes detection difficult for both humans and automated systems, highlighting the importance of modern technologies for animal monitoring. To address this issue, we present YOLO v8-SIM, an innovative detection technique specifically developed to significantly enhance the identification precision. YOLO v8-SIM utilizes a sophisticated dual-layer attention mechanism, an optimized loss function called inner intersection-over-union (IoU), and a technique called slim-neck cross-layer hopping. The results of our study demonstrate that the model achieves an accuracy rate of 91 %, a recall rate of 89.9 %, and a mean average precision (mAP) of 92.3 % and an IoU threshold of 0.5. In addition, the model operates at a frame rate of 72.21 frames per second (FPS) and excels at accurately recognizing objects that are partially visible or smaller in size. To further improve our initiatives, we suggest creating an open-source collection of data that showcases A. sinensis in its native environment while using camouflage techniques. These developments collectively enhance the ability to detect disguised animals, thereby promoting the monitoring and protection of biodiversity, and supporting ecosystem sustainability.

A Global Database of Pitted Cones on Mars for Research on Martian Volcanism

This study presents a global database of pitted cones on Mars. This database was created using an active deep-learning approach based on a global mosaic of Mars Context Camera (CTX) images, followed by extensive manual verification. The global database contains 250,547 pitted cones along with their central coordinates and diameters. 94.2% of the pitted cones have diameters ranging from 100 m to 1 km. Most of them are in the northern lowlands, while some are scattered in the southern highlands. Systematic evaluation of the extracted pitted cones is performed in Isidis Planitia, Acidalia Planitia, and Cerberus Palus on Mars. The results reveal that the precision ranges from 79.2% to 85.6%, and the recall rate ranges from 62.4% to 87.7%, indicating a varying among regions but satisfactory performance. Manual digitizing evaluation indicates that over 94.1% of manual labels by different annotators have a differentiation rate of 10%, showing promising precision and consistency. This global database can facilitate further research on the origin and evolution of pitted cones on Mars.

Enhancing autonomous pavement crack detection: Optimizing YOLOv5s algorithm with advanced deep learning techniques

To enhance the safety and comfort of vehicle travel, detecting pavement cracks is a critical task in road management. This article introduces an advanced single-stage target detection method utilizing the YOLOv5s algorithm to enhance real-time performance and accuracy. Initially, Squeeze-and-Excitation Networks are integrated into the model to facilitate self-learning for improved crack characterization. Subsequently, anchors computed through the K-means clustering algorithm are closely aligned with the fracture dataset, achieving an adaptation rate of 99.9 % and enhancing the recall rate of the model. Furthermore, the inclusion of the SimSPPF module from YOLOv6 diminishes memory usage and expedites detection speed. By replacing the original nearest up-sampling method with transposed convolution, optimization of up-sampling for crack datasets is achieved. Performance assessments reveal that the refined YOLOv5s algorithm attains an F1 score of 91 %, a mean Average Precision (mAP) of 93.6 %, and a 1.54 % increase in frames per second (fps) for pavement crack detection. This enhancement in detection technology signifies a substantial advancement in the maintenance and longevity of road infrastructure.

Characterizing features affecting local ancestry inference performance in admixed populations.

In recent years, significant efforts have been made to improve methods for genomic studies of admixed populations using Local Ancestry Inference (LAI). Accurate LAI is crucial to ensure downstream analyses reflect the genetic ancestry of research participants accurately. Here, we test analytic strategies for LAI to provide guidelines for optimal accuracy, focusing on admixed populations reflective of Latin America's primary continental ancestries - African (AFR), Amerindigenous (AMR), and European (EUR). Simulating LD-informed admixed haplotypes under a variety of 2 and 3-way admixture models, we implemented a standard LAI pipeline, testing three reference panel compositions to quantify their overall and ancestry-specific accuracy. We examined LAI miscall frequencies and true positive rates (TPR) across simulation models and continental ancestries. AMR tracts have notably reduced LAI accuracy as compared to EUR and AFR tracts in all comparisons, with TPR means for AMR ranging from 88-94%, EUR from 96-99% and AFR 98-99%. When LAI miscalls occurred, they most frequently erroneously called European ancestry in true Amerindigenous sites. Using a reference panel well-matched to the target population, even with a lower sample size, LAI produced true-positive estimates that were not statistically different from a high sample size but mismatched reference, while being more computationally efficient. While directly responsive to admixed Latin American cohort compositions, these trends are broadly useful for informing best practices for LAI across other admixed populations. Our findings reinforce the need for inclusion of more underrepresented populations in sequencing efforts to improve reference panels.

COVID-19 severity detection using chest X-ray segmentation and deep learning

COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus’s variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework’s reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings.

Lightweight Algorithm for Rail Fastener Status Detection Based on YOLOv8n

To improve the accuracy of rail fastener detection and deploy deep learning models on mobile platforms for fast real-time inference, this paper proposes a defect detection model for rail fasteners based on an improved YOLOv8n. Considering the significant aspect ratio differences of rail fasteners, we designed the EIOU+ as the regression box loss function. The model is compressed and trained using an improved channel-wise knowledge distillation (CWD+) approach to address the challenge of accurately recognizing minor defects in rail fasteners. We introduced a feature extraction module to design a feature extraction network as the distillation teacher model (YOLOv8n-T) and a lightweight cross-stage partial bottleneck with two convolutions and a fusion module (C2f) to improve the YOLOv8n backbone network as the distillation student model (YOLOv8n-S). Experiments conducted on data collected from actual rail lines demonstrate that after CWD+ distillation training, the model’s mean detection accuracy (IOU = 0.5) reached 96.3%, an improvement of 2.7% over the original YOLOv8n algorithm. The recall rate increased by 4.5%, the precision by 2.7%, the number of floating-point operations decreased by 13%, and the detection frame rate frames per second (FPS) increased by 6.1 frames per second. Compared with other one-stage object detection algorithms, the CWD+ distilled model achieves the precise real-time detection of rail fastener conditions.

Metagenomic versus targeted next-generation sequencing for detection of microorganisms in bronchoalveolar lavage fluid among renal transplantation recipients.

Metagenomic next-generation sequencing (mNGS), which provides untargeted and unbiased pathogens detection, has been extensively applied to improve diagnosis of pulmonary infection. This study aimed to compare the clinical performance between mNGS and targeted NGS (tNGS) for microbial detection and identification in bronchoalveolar lavage fluid (BALF) from kidney transplantation recipients (KTRs). BALF samples with microbiological results from mNGS and conventional microbiological test (CMT) were included. For tNGS, samples were extracted, amplified by polymerase chain reaction with pathogen-specific primers, and sequenced on an Illumina Nextseq. A total of 99 BALF from 99 KTRs, among which 93 were diagnosed as pulmonary infection, were analyzed. Compared with CMT, both mNGS and tNGS showed higher positive rate and sensitivity (p<0.001) for overall, bacterial and fungal detection. Although the positive rate for mNGS and tNGS was comparable, mNGS significantly outperformed tNGS in sensitivity (100% vs. 93.55%, p<0.05), particularly for bacteria and virus (p<0.001). Moreover, the true positive rate for detected microbes of mNGS was superior over that of tNGS (73.97% vs. 63.15%, p<0.05), and the difference was also significant when specific for bacteria (94.59% vs. 64.81%, p<0.001) and fungi (93.85% vs. 72.58%, p<0.01). Additionally, we found that, unlike most microbes such as SARS-CoV-2, Aspergillus, and EBV, which were predominantly detected from recipients who underwent surgery over 3 years, Torque teno virus (TTV) were principally detected from recipients within 1-year post-transplant, and as post-transplantation time increased, the percentage of TTV positivity declined. Although tNGS was inferior to mNGS owing to lower sensitivity and true positive rate in identifying respiratory pathogens among KTRs, both considerably outperformed CMT.