High Recall Rate Research Articles

Fruit fast tracking and recognition of apple picking robot based on improved YOLOv5

AbstractThe article proposes a real‐time apple picking method based on an improved YOLOv5. This method accurately recognizes different apple targets on fruit trees for robots and helps them adjust their position to avoid obstructions during fruit picking. Firstly, the original BottleneckCSP module in the YOLOv5 backbone network is enhanced to extract deeper features from images while maintaining lightweight. Secondly, the ECA module is embedded into the improved backbone network to better extract features of different apple targets. Lastly, the initial anchor frame size of the network is adjusted to avoid recognizing apples in distant planting rows. The results demonstrate that this improved model achieves high accuracy rates and recall rates for recognizing various types of apple picking methods with an average recognition time of 0.025s per image. Compared with other models tested on six types of apple picking methods, including the original YOLOv5 model as well as YOLOv3 and EfficientDet‐D0 algorithms, our improved model shows significant improvements in mAP by 1.95%, 17.6%, and 12.7% respectively. This method provides technical support for robots' picking hands to actively avoid obstructions caused by branches during fruit harvesting, effectively reducing apple loss.

Enhancing efficiency in emergency drug inspection through machine learning and non-destructive spectroscopy

During emergency inspections, drug control institutions often encounter samples with unknown components. It is essential to develop a method for quickly identifying these unknown components. Transforming the component analysis problem into a multi-label classification problem, this study addresses this challenge by employing non-destructive spectroscopic technology combined with machine learning. Spectral data from 368 compounds were initially collected for modeling. The ResUCA model was developed based on the residual neural network and compared with other models. Using the same data enhancement method, ResUCA outperformed the other models in terms of accuracy, recall, precision and F1_score. Subsequently, optimization was performed, considering factors such as data augmentation, spectrum selection, and sample processing, all of which impact the model's construction. Finally, the model was expanded in two steps, maintaining a consistently high recall rate, albeit with an increase in false positives. This suggests that fine-tuning the model parameters can help mitigate this challenge in various scenarios, highlighting its potential for ongoing optimization in future research efforts. Additionally, its applicability extends across diverse fields, including food, cosmetics, and coating analysis.

A Transformative Approach for Breast Cancer Detection Using Physics-Informed Neural Network and Surface Temperature Data

Abstract Early detection is the most effective defense against breast cancer. Mammography is a well-established X-ray based technique that is used for annual or biennial screening of women above age of 40. Since the dense breast tissue sometimes obscures the cancer in an x-ray image, about 10% of screened women are recalled and undergo additional adjunctive modalities, such as ultrasound, digital breast tomosynthesis or magnetic resonance imaging (MRI). These modalities have drawbacks such as additional radiation dosage, overdiagnosis and high cost. A new concurrent multi-spectral imaging approach is recently presented to eliminate the high recall rates by utilizing the breast surface temperature data with an inverse physics-informed neural network algorithm. The multi-spectral imaging does not use any harmful radiations, such as x-rays, is contact-less and does not require breast compression. It has been validated in 23 patients and offers a cost-effective solution to provide improved detection capability of cancerous cells. It is estimated to reduce the recall rates significantly from the current 10%, with a corresponding reduction in the biopsies. This adjunctive approach builds on the strength of mammography and offers a safe adjunct by relying on the higher metabolic rates of cancer cells.

Assessing the Performance of Logistic Regression in Heart Disease Detection through 5-Fold Cross-Validation

This study explores the effectiveness of Logistic Regression in predicting heart disease using a dataset derived from multiple international databases. Employing a 5-fold cross-validation method, the research aimed to evaluate the model's accuracy, precision, recall, and F1-score. Results indicated that Logistic Regression performs robustly, with accuracy ranging from 80% to 88.29%, and high recall rates, highlighting its potential as a valuable tool in medical diagnostics. Despite some variability in precision, which may lead to higher false positive rates, the model's high recall is crucial in clinical settings where missing a diagnosis can have dire consequences. The research confirmed the applicability of Logistic Regression to binary classification problems in healthcare, aligning with existing literature that supports its use in similar contexts. The study contributes to the field by demonstrating the model's consistency and reliability across diverse data subsets, reinforcing the potential for machine learning applications in healthcare diagnostics. Future research should focus on integrating Logistic Regression with other models to improve accuracy and testing the model on more current, varied datasets to enhance its generalizability and effectiveness in real-world settings.

Exploring End-to-End object detection with transformers versus YOLOv8 for enhanced citrus fruit detection within trees

This paper presents a comparative analysis between two state-of-the-art object detection models, DETR and YOLOv8, focusing on their effectiveness in fruit detection for yield prediction in agriculture. The study begins with data acquisition, utilizing images and corresponding annotations to train and evaluate the models. Our approach employs a data-driven methodology, dividing the dataset into training and testing sets, with rigorous validation to ensure robustness.For DETR, evaluation results demonstrate promising performance across various IoU thresholds, indicating its effectiveness in accurately localizing fruits within bounding boxes. Additionally, YOLOv8 exhibits substantial improvements in detection performance, achieving high precision and recall rates, particularly noteworthy for "orange" and "sweet_orange" classes. Notably, the model showcases commendable proficiency even in challenging scenarios.In conclusion, both DETR and YOLOv8 offer valuable insights for precision farming, aiding farmers in yield prediction and harvest planning. While DETR demonstrates robustness and efficiency in fruit detection, YOLOv8 excels in high-precision detection, albeit with longer training times. These findings highlight the potential of advanced object detection models in revolutionizing agricultural practices, contributing to enhanced productivity and market equilibrium.

Data-driven automatic classification model for construction accident cases using natural language processing with hyperparameter tuning

The construction industry, while vital to societal progress, is marred by a high incidence of accidents and injuries. Manual classification of accident cases is intensive and susceptible to human bias. This study addresses this challenge by developing an automated accident case classification system for the construction industry using Natural Language Processing and machine learning techniques. This study was conducted using the following steps: (1) Establishment of dataset (2) Korean Natural Language Processing (3) Selection of machine learning models (4) Model evaluation. The models exhibited competitive performance, demonstrating high accuracy, precision, and recall rates across all classification tasks. XGBoost outperformed NB, SVM, and KNN for accident type, facility type, and work type with accuracy of 0.80, 0.56, and 0.67, respectively. The results also provided insights into the factors influencing accident classification. This study contributes to construction safety by providing a data-driven foundation for safety decision-making, resource allocation, and benchmarking.

TARGET RECOGINITION AND DETECTION USING DEEP LEARING TECHNIQUE

Object detection is a fundamental computer vision function for identifying and locating things in images or videos. Unlike image classification, object detection not only classifies the items in an image but also locates them inside the picture by constructing a bounding box around each one. Defence objects include a wide range of key assets needed for military and security activities. Tanks, armoured personnel carriers (APCs), military trucks, planes, helicopters, naval boats, and unmanned ground vehicles (UGVs) are among the types of vehicles included. Detection of these vehicles is critical for tracking troop movements, analysing battlefield dynamics, and maintaining operational preparedness. The modern defence scenario demands improved surveillance and security measures to successfully counter growing threats. This work suggests using the You Only Look Once (YOLO) method for real-time identification of numerous defence items. The project's goal is to improve security by properly detecting a variety of items, including cars, individuals, equipment, and structures, with a single deep learning model. Methodologically, a broad dataset containing photos and videos of defence items in various locations is collected and preprocessed. The YOLO algorithm is then trained on this dataset, with parameters optimised for high accuracy and recall rates. Performance evaluation include thorough testing on various datasets to determine accuracy, speed, and resilience. KEYWORDS: Target recognition, Detection, YOLO algorithm, Military applications, Flying objects, Vehicles, Sensor integration, Real-time processing, Threat detection, Situational awareness.

Abstract PO1-10-09: The Performance Of Mobile Units Versus Hospital Units In National Breast Cancer Screening Program In Taiwan, 2010-2020

Abstract Purpose After the implementation of mobile units, the screened population increased from 3.9% to 40% of all women from 2004 to 2019 in Taiwan’s Breast Cancer Screening Program. There are limited studies comparing mobile units to hospital units. This study evaluated and compared the performance of the biennial mammography breast cancer screening in mobile units to hospital units in Taiwan over the past decade. Methods A cohort of 3 062 190 women aged 40 to 69 years who underwent biennial breast cancer mammography screenings from 2010 to 2020 was conducted, and data were obtained from the Health Promotion Administration, Ministry of Health and Welfare of Taiwan. Comparing participation of screened women mobile units and hospital units across national screening. Performance measures were determined as percentages and 95% confidence intervals (CIs) using the Wald asymptotic method. Results Among 3 062 190 women who underwent 7 444 450 examinations in the study population, the screened population by mobile units accounted for approximately 45.45 % of total examinations. The volume of screening mammograms performed in the mobile unit increased the number of people reached by this program. Since 2015, screenings performed in the mobile units have outnumbered those performed at brick-and-mortar hospitals: they comprised 480 456 of the 859 221 examinations (55.9%) performed in 2019. During the 10-year periods, the screen-detected cancers were 12 000 and 18 370 for mobile units and hospital units, respectively. Young women preferred screening in hospitals, resulting in a greater proportion of screen-detected cancers among those attending hospitals (49.4%) compared to the mobile unit (34.3%). The mean recall rate was higher in the hospitals at 8.95% (95% CI, 8.93%-8.99%) than in the mobile units at 7.27% (95% CI, 7.25%-7.32%). Conclusion Implementing mobile units increased the coverage of the screening program across the population. Hospital units had a younger patient population and higher recall rate than those mobile units. We can enhance mammography screening rates and follow-up among these groups by identifying these features, which can use to develop programs and materials fitting populations' specific requirements. Summary statement In Taiwan, the development of breast cancer screening has shown beneficial outcomes, especially with the deployment of mobile unit services to increase screened women. Our results could serve as an informative reference for other nations. Keywords: Breast cancer; screening; mobile units; hospital units. Table 1. Clinical Demographics for Mammographic Screening Examinations Table 2. Performance Measures of Digital Mammographic Screenings for Breast Cancer Citation Format: Vy Vu, Amy Ming-Fang Yen, Melissa Min-Szu Yao, Wing P. Chan. The Performance Of Mobile Units Versus Hospital Units In National Breast Cancer Screening Program In Taiwan, 2010-2020 [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-10-09.

CenterNet++ for Object Detection.

There are two mainstream approaches for object detection: top-down and bottom-up. The state-of-the-art approaches are mainly top-down methods. In this paper, we demonstrate that bottom-up approaches show competitive performance compared with top-down approaches and have higher recall rates. Our approach, named CenterNet, detects each object as a triplet of keypoints (top-left and bottom-right corners and the center keypoint). We first group the corners according to some designed cues and confirm the object locations based on the center keypoints. The corner keypoints allow the approach to detect objects of various scales and shapes and the center keypoint reduces the confusion introduced by a large number of false-positive proposals. Our approach is an anchor-free detector because it does not need to define explicit anchor boxes. We adapt our approach to backbones with different structures, including 'hourglass'-like networks and 'pyramid'-like networks, which detect objects in single-resolution and multi-resolution feature maps, respectively. On the MS-COCO dataset, CenterNet with Res2Net-101 and Swin-Transformer achieve average precisions (APs) of 53.7% and 57.1%, respectively, outperforming all existing bottom-up detectors and achieving state-of-the-art performance. We also design a real-time CenterNet model, which achieves a good trade-off between accuracy and speed, with an AP of 43.6% at 30.5 frames per second (FPS).

EA-GAT: Event aware graph attention network on cyber-physical systems

Anomaly detection with high accuracy, recall, and low error rate is critical for the safe and uninterrupted operation of cyber-physical systems. However, detecting anomalies in multimodal time series with different modalities obtained from cyber-physical systems is challenging. Although deep learning methods show very good results in anomaly detection, they fail to detect anomalies according to the requirements of cyber-physical systems. In the use of graph-based methods, data loss occurs during the conversion of time series into graphs. The fixed window size used to transform time series into graphs causes a loss of spatio-temporal correlations. In this study, we propose an Event Aware Graph Attention Network (EA-GAT), which can detect anomalies by event-based cyber-physical system analysis. EA-GAT detects and tracks the sensors in cyber-physical systems and the correlations between them. The system analyzes and models the relationship between the components during the marked periods as a graph. Anomalies in the system are found through the created graph models. Experiments show that the EA-GAT technique is more effective than other deep learning methods on SWaT, WADI, MSL datasets used in various studies. The event-based dynamic approach is significantly superior to the fixed-size sliding window technique, which uses the same learning structure. In addition, anomaly analysis is used to identify the attack target and the affected components. At the same time, with the slip subsequence module, the data is divided into subgroups and processed simultaneously.

PheSeq, a Bayesian deep learning model to enhance and interpret the gene-disease association studies

Despite the abundance of genotype-phenotype association studies, the resulting association outcomes often lack robustness and interpretations. To address these challenges, we introduce PheSeq, a Bayesian deep learning model that enhances and interprets association studies through the integration and perception of phenotype descriptions. By implementing the PheSeq model in three case studies on Alzheimer’s disease, breast cancer, and lung cancer, we identify 1024 priority genes for Alzheimer’s disease and 818 and 566 genes for breast cancer and lung cancer, respectively. Benefiting from data fusion, these findings represent moderate positive rates, high recall rates, and interpretation in gene-disease association studies.

U-Net for genomic sequencing: A novel approach to DNA sequence classification

The precise classification of DNA sequences is pivotal in genomics, holding significant implications for personalized medicine. The stakes are particularly high when classifying key genetic markers such as BRAC, related to breast cancer susceptibility; BRAF, associated with various malignancies; and KRAS, a recognized oncogene. Conventional machine learning techniques often necessitate intricate feature engineering and may not capture the full spectrum of sequence dependencies. To ameliorate these limitations, this study employs an adapted U-Net architecture, originally designed for biomedical image segmentation, to classify DNA sequences.The attention mechanism was also tested LONG WITH u-Net architecture to precisely classify DNA sequences into BRAC, BRAF, and KRAS categories. Our comprehensive methodology includes rigorous data preprocessing, model training, and a multi-faceted evaluation approach. The adapted U-Net model exhibited exceptional performance, achieving an overall accuracy of 0.96. The model also achieved high precision and recall rates across the classes, with precision ranging from 0.93 to 1.00 and recall between 0.95 and 0.97 for the key markers BRAC, BRAF, and KRAS. The F1-score for these critical markers ranged from 0.95 to 0.98. These empirical results substantiate the architecture's capability to capture local and global features in DNA sequences, affirming its applicability for critical, sequence-based bioinformatics challenges.

Anomaly Detection for Landslide Displacement Monitoring Data Based on TCN-Transformer

In view of the high false alarm rate of landslide early warning, this paper proposes a classification method of landslide displacement monitoring data based on TCN and attention mechanism to identify normal data and abnormal data. First, the original monitoring data is processed and denoised to improve the data quality. Then, TCN is used to capture the long-term dependence of time series data and highlight key features in combination with attention mechanism. Finally, the landslide displacement monitoring data can be accurately classified by building a classification model to find out the abnormal data and reduce the false alarm rate of early warning. Experiments show that this method can recognize abnormal displacement monitoring data well while ensuring a high recall rate, and reduce the false alarm rate of early warning.

Enhancing Wireless Sensor Network Security Through Mutual Information Analysis for Intrusion Detection and Resilience

Intrusion detection is a critical aspect of network security, involving the identification and response to unauthorized access or malicious activities within a system. It plays a crucial role in safeguarding networks and ensuring data integrity and confidentiality. The Mutual Information (MI) analysis is a vital component in the realm of intrusion detection and security within Wireless Sensor Networks (WSNs). By assessing the information shared between pairs of sensor nodes, MI analysis reveals underlying patterns and relationships in network data. This process involves calculating the mutual information for each node pair based on statistical properties of observed values. Strong correlations or dependencies between nodes are identified, aiding in the detection of critical nodes or clusters vulnerable to compromise. Additionally, MI analysis informs feature extraction by guiding the selection of informative features that capture network structure. It also serves as a proactive tool for identifying anomalies or deviations from expected patterns, which may signal intrusion attempts or malicious activities. Through monitoring changes in mutual information over time, MI analysis facilitates prompt responses to emerging threats, enhancing the resilience and security of WSNs. The work exhibits high accuracy, recall rates, and detection rates across various attack scenarios, underscoring its efficacy in identifying and mitigating security threats. The algorithm's efficiency, effectiveness, and reliability make it a promising solution for enhancing WSN security. Through sophisticated methodologies and adaptive defensive strategies, the proposed algorithm strengthens the robustness and dependability of WSNs, minimizing the risk of potential security vulnerabilities and ensuring comprehensive threat detection in real-world deployment scenarios.

Structural entropy minimization combining graph representation for money laundering identification

Money laundering identification (MLI) is a challenging task for financial AI research and application due to its massive transaction volume, label sparseness, and label bias. Most of the existing MLI methods focus on individual-level abnormal behavior while neglecting the community factor that money laundering is a collaborative group crime. Furthermore, the massive volume of transactions and the issue of label shifting also impede the application of supervised or semi-supervised models. To this end, this paper proposes an efficient community-oriented algorithm, namely SEGE, to identify money laundering based on structural entropy minimization (SEM) with graph embedding in an unsupervised approach. Experiments on both a private real-world money laundering network and a public synthetic dataset show that our SEGE algorithm derives prominent performance and outperforms the parameterized learning-based graph representation methods. Moreover, we find that there are pervasive sub-communities in the real-world money laundering network. Based on our local algorithm, we propose a real combat strategy against the money laundering group, in which when we have several scattered suspicious accounts in the transaction network, we are able to retrieve the whole money laundering group by the union of sub-communities with both high precision and high recall rates.

DIAmante TESS AutoRegressive Planet Search (DTARPS). I. Analysis of 0.9 Million Light Curves

Nearly one million light curves from the TESS Year 1 southern hemisphere extracted from Full Field Images with the DIAmante pipeline are processed through the AutoRegressive Planet Search statistical procedure. ARIMA models remove lingering autocorrelated noise, the Transit Comb Filter identifies the strongest periodic signal in the light curve, and a Random Forest machine-learning classifier is trained and applied to identify the best potential candidates. Classifier training sets are based on injections of planetary transit signals, eclipsing binaries, and other variable stars. The optimized classifier has a True Positive Rate of 92.5% and a False Positive Rate of 0.43% from the labeled training set. The result of this DIAmante TESS autoregressive planet search of the southern ecliptic hemisphere analysis is a list of 7377 potential exoplanet candidates. The classifier had a 64% recall rate for previously confirmed exoplanets and a 78% negative recall rate for known False Positives. The completeness map of the injected planetary signals shows high recall rates for planets with 8–30R ⊕ radii and periods 0.6–13 days and poor completeness for planets with radii <2R ⊕ or periods <1 day. The list has many False Alarms and False Positives that need to be culled with multifaceted vetting operations (Paper II).

Cn2a-capsnet: a capsule network and CNN-attention based method for COVID-19 chest X-ray image diagnosis

Due to its high infectivity, COVID-19 has rapidly spread worldwide, emerging as one of the most severe and urgent diseases faced by the global community in recent years. Currently, deep learning-based diagnostic methods can automatically detect COVID-19 cases from chest X-ray images. However, these methods often rely on large-scale labeled datasets. To address this limitation, we propose a novel neural network model called CN2A-CapsNet, aiming to enhance the automatic diagnosis of COVID-19 in chest X-ray images through efficient feature extraction techniques. Specifically, we combine CNN with an attention mechanism to form the CN2A model, which efficiently mines relevant information from chest X-ray images. Additionally, we incorporate capsule networks to leverage their ability to understand spatial information, ultimately achieving efficient feature extraction. Through validation on a publicly available chest X-ray image dataset, our model achieved a 98.54% accuracy and a 99.01% recall rate in the binary classification task (COVID-19/Normal) on a six-fold cross-validation dataset. In the three-class classification task (COVID-19/Pneumonia/Normal), it attained a 96.71% accuracy and a 98.34% recall rate. Compared to the previous state-of-the-art models, CN2A-CapsNet exhibits notable advantages in diagnosing COVID-19 cases, specifically achieving a high recall rate even with small-scale datasets.

Intrusion Detection using Network Traffic Profiling and Machine Learning for IoT

The proliferation of the Internet of Things (IoT) in various sectors, including healthcare, smart cities, and industrial automation, has significantly enhanced operational efficiency and service delivery. However, this widespread adoption has introduced new vulnerabilities, making IoT networks a prime target for cyberattacks. Traditional security mechanisms often fall short in protecting IoT devices due to their limited computational resources and the unique nature of IoT network traffic. This paper introduces a novel intrusion detection system (IDS) that leverages network traffic profiling and machine learning techniques tailored for the IoT ecosystem. By analyzing the behavioral patterns of network traffic, the proposed system can accurately identify malicious activities and potential threats in real-time, ensuring the integrity and confidentiality of IoT networks. The methodology encompasses data collection, feature extraction, model training, and evaluation stages, employing a combination of supervised and unsupervised machine learning algorithms to optimize detection accuracy. Experimental results, conducted on real-world IoT network datasets, demonstrate the effectiveness of our approach in detecting a wide range of cyber threats with high precision and recall rates. This research contributes to the cybersecurity domain by providing a scalable, efficient, and adaptive IDS framework that can be integrated into various IoT infrastructures to mitigate the risk of cyber intrusions.

Detecting Cyber-attacks in the Industrial Internet of Things using a Hybrid Deep Random Neural Network

Critical infrastructure now faces greater vulnerabilities and a higher risk of cyberattacks as a result of the (IIoT) quick expansion. The security and dependability of industrial systems must be ensured by identifying and thwarting these threats. In this paper, we use a hybrid approach of deep learning and RNN called hybrid deep random neural network (HDRNN) to offer a novel method of identifying cyber-attacks in the IIoT.The proposed HDRNN model combines the benefits of random neural networks with deep learning to improve the detection of IIoT cyberattacks. The deep learning component makes use of deep neural networks' capacity to extract intricate features from unstructured data, while the random neural network component offers robustness and adaptability to manage changing attack patterns.Realistic threats and benchmark datasets such as UNSW-NB15and DS2OS are used in experimental evaluations. High accuracy, precision, and recall rates are attained by the model, which successfully detects a variety of assaults including infiltration, data manipulation, and denial of service.The suggested HDRNN model offers a promising approach for improving the security of IIoT systems by precisely identifying cyber-attacks in real-time. The model's hybrid nature enables enhanced detection capabilities, adaptability to changing attack patterns, and a reduction in false positives, enabling efficient threat mitigation and protecting crucial infrastructure in the IIoT context.

Fostering idealogical and polical education via knowledge graph and KNN model: an emphasis on positive psychology

As the primary domain of ideological and political education in higher education institutions, ideological and political courses must align with principles rooted in human psychology and education. Integrating educational psychology into ideological and political teaching in universities enhances the scientific, targeted, and forward-thinking nature of such education. The burgeoning exploration of knowledge graph applications has extended to machine translation, semantic search, and intelligent question answering. Diverging from traditional text matching, the knowledge spectrum graph transforms information acquisition in search engines. This paper pioneers a predictive system for delineating the relationship between educational psychology and ideological and political education in universities. Initially, it extracts diverse psychological mapping relationships of students, constructing a knowledge graph. By employing the KNN algorithm, the system analyzes psychological characteristics to effectively forecast the relationship between educational psychology and ideological and political education in universities. The system's functionality is meticulously detailed in this paper, and its performance is rigorously tested. The results demonstrate high accuracy, recall rates, and F1 values. The F1 score can reach 0.95enabling precise sample classification. The apex of the average curve for system response time peaks at approximately 2.5 s, maintaining an average response time of less than 3 s. This aligns seamlessly with the demands of practical online teaching requirements. The system adeptly forecasts the relationship between educational psychology and ideological and political education in universities, meeting response time requirements and thereby fostering the scientific and predictive nature of ideological and political teaching in higher education institutions.