Mean Average Precision Research Articles

A Deep-Learning-Based Model for the Detection of Diseased Tomato Leaves

This study introduces a You Only Look Once (YOLO) model for detecting diseases in tomato leaves, utilizing YOLOV8s as the underlying framework. The tomato leaf images, both healthy and diseased, were obtained from the Plant Village dataset. These images were then enhanced, implemented, and trained using YOLOV8s using the Ultralytics Hub. The Ultralytics Hub provides an optimal setting for training YOLOV8 and YOLOV5 models. The YAML file was carefully programmed to identify sick leaves. The results of the detection demonstrate the resilience and efficiency of the YOLOV8s model in accurately recognizing unhealthy tomato leaves, surpassing the performance of both the YOLOV5 and Faster R-CNN models. The results indicate that YOLOV8s attained the highest mean average precision (mAP) of 92.5%, surpassing YOLOV5’s 89.1% and Faster R-CNN’s 77.5%. In addition, the YOLOV8s model is considerably smaller and demonstrates a significantly faster inference speed. The YOLOV8s model has a significantly superior frame rate, reaching 121.5 FPS, in contrast to YOLOV5’s 102.7 FPS and Faster R-CNN’s 11 FPS. This illustrates the lack of real-time detection capability in Faster R-CNN, whereas YOLOV5 is comparatively less efficient than YOLOV8s in meeting these needs. Overall, the results demonstrate that the YOLOV8s model is more efficient than the other models examined in this study for object detection.

One-Year-Old Precocious Chinese Mitten Crab Identification Algorithm Based on Task Alignment.

The cultivation of the Chinese mitten crab (Eriocheir sinensis) is an important component of China's aquaculture industry and also a field of concern worldwide. It focuses on the selection of high-quality, disease-free juvenile crabs. However, the early maturity rate of more than 18.2% and the mortality rate of more than 60% make it difficult to select suitable juveniles for adult culture. The juveniles exhibit subtle distinguishing features, and the methods for differentiating between sexes vary significantly; without training from professional breeders, it is challenging for laypersons to identify and select the appropriate juveniles. Therefore, we propose a task-aligned detection algorithm for identifying one-year-old precocious Chinese mitten crabs, named R-TNET. Initially, the required images were obtained by capturing key frames, and then they were annotated and preprocessed by professionals to build a training dataset. Subsequently, the ResNeXt network was selected as the backbone feature extraction network, with Convolutional Block Attention Modules (CBAMs) and a Deformable Convolution Network (DCN) embedded in its residual blocks to enhance its capability to extract complex features. Adaptive spatial feature fusion (ASFF) was then integrated into the feature fusion network to preserve the detailed features of small targets such as one-year-old precocious Chinese mitten crab juveniles. Finally, based on the detection head proposed by task-aligned one-stage object detection, the parameters of its anchor alignment metric were adjusted to detect, locate, and classify the crab juveniles. The experimental results showed that this method achieves a mean average precision (mAP) of 88.78% and an F1-score of 97.89%. This exceeded the best-performing mainstream object detection algorithm, YOLOv7, by 4.17% in mAP and 1.77% in the F1-score. Ultimately, in practical application scenarios, the algorithm effectively identified one-year-old precocious Chinese mitten crabs, providing technical support for the automated selection of high-quality crab juveniles in the cultivation process, thereby promoting the rapid development of aquaculture and agricultural intelligence in China.

Crowd Density Level Classification for Service Waiting Room Based on Head Detection to Enhance Visitor Experience

The crowd within a confined space can potentially lead to air stagnation in waiting areas. Constantly running air conditioning throughout the day to balance air circulation may result in excessive energy consumption by the building. To address this issue, Heating, Ventilating, and Air-Conditioning (HVAC) systems are employed to manage and regulate indoor energy usage. However, sensor-based detection often fails to capture human variables promptly, resulting in less accurate density readings. Camera footage proves to be more reliable than sensors in accurately detecting crowds. This research utilizes You Only Look Once version 8 (YOLOv8), a robust algorithm for object detection, particularly effective in crowd detection for images, along with Convolutional Vision Transformer (CvT) for crowd density level classification into "Normal" and "Crowded" levels. CvT enhances classification accuracy by incorporating function from Convolutional Neural Network (CNN) in model training, including receptive field, shared weights, etc. By integrating YOLOv8 and CvT, this method focuses on accurately classifying crowd density levels after identifying human presence in the waiting area (indoor). Evaluation metrics include mean Average Precision (mAP) for YOLOv8, and accuracy, precision, recall, and f1-score for CvT. This approach directly influences the management of HVAC systems.

Advancing jasmine tea production: YOLOv7-based real-time jasmine flower detection.

To produce jasmine tea of excellent quality, it is crucial to select jasmine flowers at their optimal growth stage during harvesting. However, achieving this goal remains a challenge due to environmental and manual factors. This study addresses this issue by classifying different jasmine flowers based on visual attributes using the YOLOv7 algorithm, one of the most advanced algorithms in convolutional neural networks. The mean average precision (mAP value) for detecting jasmine flowers using this model is 0.948, and the accuracy for five different degrees of openness of jasmine flowers, namely small buds, buds, half-open, full-open and wiltered, is 87.7%, 90.3%, 89%, 93.9% and 86.4%, respectively. Meanwhile, other ways of processing the images in the dataset, such as blurring and changing the brightness, also increased the credibility of the algorithm. This study shows that it is feasible to use deep learning algorithms for distinguishing jasmine flowers at different growth stages. This study can provide a reference for jasmine production estimation and for the development of intelligent and precise flower-picking applications to reduce flower waste and production costs. © 2024 Society of Chemical Industry.

Question Answering System Based on Bideirectional Long-Short-Term Memory (Bilstm)

In the modern world, Q&A systems are essential for promoting better communication between people and technology. These systems play an important role in collecting information quickly and efficiently, and this leads to great progress in learning, teaching and development in many areas of life. Using deep learning techniques, this research addresses the problem of excellent prediction of the questions that need to be answered. We created a question-and-answer system using "Bidirectional Long Short-Term Memory (BiLSTM)", a modern neural network known for its accuracy and results in text analysis and natural language understanding. This technique is more effective in understanding questions and producing very accurate answers because of its special ability to pay attention to preceding and following information in a sentence. Preprocessing was used to remove unnecessary, unimportant and time-consuming data. The "Stanford Question Answering Dataset version 2 (SQuAD 2.0)"was used, which is considered one of the important datasets used in the field of machine learning and natural language processing. The following evaluation metrics were used to evaluate the model’s performance: “Mean Average Precision(MAP), Mean Reciprocal Rank(MRR), Recall, Precision, Loss, F1 Score, and Exact Match (EM). The results, based on 150 epochs (EPOGs) and 128 batch sizes with a cleaned dataset split into 70% training and 30% test/validation (15% each), are as follows:"Precision (0.966), Loss (0.591), F1-score (0.966), Recall (0.967), EM (0.967), MRR(0.918), MAP (0.776), and accuracy(0.966)". Interestingly, the highest performance was observed when using the accuracy measure.

A Multitask Learning-Based Vision Transformer for Plant Disease Localization and Classification

Plant disease detection is a critical task in agriculture, essential for ensuring crop health and productivity. Traditional methods in this context are often labor-intensive and prone to errors, highlighting the need for automated solutions. While computer vision-based solutions have been successfully deployed in recent years for plant disease identification and localization tasks, these often operate independently, leading to suboptimal performance. It is essential to develop an integrated solution combining these two tasks for improved efficiency and accuracy. This research proposes the innovative Plant Disease Localization and Classification model based on Vision Transformer (PDLC-ViT), which integrates co-scale, co-attention, and cross-attention mechanisms and a ViT, within a Multi-Task Learning (MTL) framework. The model was trained and evaluated on the Plant Village dataset. Key hyperparameters, including learning rate, batch size, dropout ratio, and regularization factor, were optimized through a thorough grid search. Early stopping based on validation loss was employed to prevent overfitting. The PDLC-ViT model demonstrated significant improvements in plant disease localization and classification tasks. The integration of co-scale, co-attention, and cross-attention mechanisms allowed the model to capture multi-scale dependencies and enhance feature learning, leading to superior performance compared to existing models. The PDLC-ViT model evaluated on two public datasets achieved an accuracy of 99.97%, a Mean Average Precision (MAP) of 99.18%, and a Mean Average Recall (MAR) of 99.11%. These results underscore the model's exceptional precision and recall, highlighting its robustness and reliability in detecting and classifying plant diseases. The PDLC-ViT model sets a new benchmark in plant disease detection, offering a reliable and advanced tool for agricultural applications. Its ability to integrate localization and classification tasks within an MTL framework promotes timely and accurate disease management, contributing to sustainable agriculture and food security.

Efficient forest fire detection based on an improved YOLO model

A forest fire is a natural disaster characterized by rapid spread, difficulty in extinguishing, and widespread destruction, which requires an efficient response. Existing detection methods fail to balance global and local fire features, resulting in the false detection of small or hidden fires. In this paper, we propose a novel detection technique based on an improved YOLO v5 model to enhance the visual representation of forest fires and retain more information about global interactions. We add a plug-and-play global attention mechanism to improve the efficiency of neck and backbone feature extraction of the YOLO v5 model. Then, a re-parameterized convolutional module is designed, and a decoupled detection head is used to accelerate the convergence speed. Finally, a weighted bi-directional feature pyramid network (BiFPN) is introduced to merge feature information for local information processing. In the evaluation, we use the complete intersection over union (CIoU) loss function to optimize the multi-task loss for different kinds of forest fires. Experiments show that the precision, recall, and mean average precision are increased by 4.2%, 3.8%, and 4.6%, respectively, compared with the classic YOLO v5 model. In particular, the mAP@0.5:0.95 is 2.2% higher than the other detection methods, while meeting the requirements of real-time detection.

Automatic deep learning detection of overhanging restorations in bitewing radiographs.

This study aimed to assess the effectiveness of deep convolutional neural network (CNN) algorithms for the detecting and segmentation of overhanging dental restorations in bitewing radiographs. A total of 1160 anonymized bitewing radiographs were used to progress the artificial intelligence (AI) system for the detection and segmentation of overhanging restorations. The data were then divided into three groups: 80% for training (930 images, 2399 labels), 10% for validation (115 images, 273 labels), and 10% for testing (115 images, 306 labels). A CNN model known as You Only Look Once (YOLOv5) was trained to detect overhanging restorations in bitewing radiographs. After utilizing the remaining 115 radiographs to evaluate the efficacy of the proposed CNN model, the accuracy, sensitivity, precision, F1 score, and area under the receiver operating characteristic curve (AUC) were computed. The model demonstrated a precision of 90.9%, a sensitivity of 85.3%, and an F1 score of 88.0%. Furthermore, the model achieved an AUC of 0.859 on the receiver operating characteristic (ROC) curve. The mean average precision (mAP) at an intersection over a union (IoU) threshold of 0.5 was notably high at 0.87. The findings suggest that deep CNN algorithms are highly effective in the detection and diagnosis of overhanging dental restorations in bitewing radiographs. The high levels of precision, sensitivity, and F1 score, along with the significant AUC and mAP values, underscore the potential of these advanced deep learning techniques in revolutionizing dental diagnostic procedures.

Automated Surface Crack Detection in Historical Constructions with Various Materials Using Deep Learning-Based YOLO Network

ABSTRACT Cultural heritage (CH) constructions involve the use of diverse masonry materials. Under natural and human influences, masonry materials can undergo various types of damages, with crack damages being most prevalent. Developing a robust model using deep learning (DL) capable of detecting cracks in various CH materials is crucial. In this study, we compared the performance of the DL method You Only Look Once (YOLO) object detection network based on images in different masonry materials (stone, brick, cob, and tile) with that in a modern material (concrete). The dataset used in the study comprised 1213 bricks, 1116 concretes, 955 cobs, 882 stones, and 208 tile images. YOLOv5 architecture, transfer learning, and object detection models were utilized for detecting cracks and compare their performance in different materials. This study represents the first comparison of this kind using an original dataset. The DL model achieved mean average precision values of 94.4%, 93.9%, 92.7%, 87.2%, 83.4%, 81.6%, and 70.3% for concrete; concrete and cob, cob; stone; stone and brick; brick; and tile, respectively. The findings of this study indicate considerable potential for the widespread use of DL techniques in identifying cracks from images across various CH materials and assisting inspection professionals in damage surveys.

Intelligent Inspection Method and System of Plastic Gear Surface Defects Based on Adaptive Sample Weighting Deep Learning Model.

After injection molding, plastic gears often exhibit surface defects, including those on end faces and tooth surfaces. These defects encompass a wide range of types and possess complex characteristics, which pose challenges for inspection. Current visual inspection systems for plastic gears suffer from limitations such as single-category defect inspection and low accuracy. There is an urgent industry need for a comprehensive and accurate method and system for inspecting defects on plastic gears, with improved inspection capability and higher accuracy. This paper presents an intelligent inspection algorithm network for plastic gear defects (PGD-net), which effectively captures subtle defect features at arbitrary locations on the surface compared to other models. An adaptive sample weighting method is proposed and integrated into an improved Focal-IoU loss function to address the issue of low inspection accuracy caused by imbalanced defect dataset distributions, thus enhancing the regression accuracy for difficult defect categories. CoordConv layers are incorporated into each inspection head to improve the model's generalization capability. Furthermore, a dataset of plastic gear surface defects comprising 16 types of defects is constructed, and our algorithm is trained and tested on this dataset. The PGD-net achieves a comprehensive mean average precision (mAP) value of 95.6% for the 16 defect types. Additionally, an online inspection system is developed based on the PGD-net algorithm, which can be integrated with plastic gear production lines to achieve online full inspection and automatic sorting of plastic gear defects. The entire system has been successfully applied in plastic gear production lines, conducting daily inspections of over 60,000 gears.

Non-volatile 2D MoS2/black phosphorus heterojunction photodiodes in the near- to mid-infrared region

Cutting-edge mid-wavelength infrared (MWIR) sensing technologies leverage infrared photodetectors, memory units, and computing units to enhance machine vision. Real-time processing and decision-making challenges emerge with the increasing number of intelligent pixels. However, current operations are limited to in-sensor computing capabilities for near-infrared technology, and high-performance MWIR detectors for multi-state switching functions are lacking. Here, we demonstrate a non-volatile MoS2/black phosphorus (BP) heterojunction MWIR photovoltaic detector featuring a semi-floating gate structure design, integrating near- to mid-infrared photodetection, memory and computing (PMC) functionalities. The PMC device exhibits the property of being able to store a stable responsivity, which varies linearly with the stored conductance state. Significantly, device weights (stable responsivity) can be programmed with power consumption as low as 1.8 fJ, and the blackbody peak responsivity can reach 1.68 A/W for the MWIR band. In the simulation of Faster Region with convolution neural network (CNN) based on the FLIR dataset, the PMC hardware responsivity weights can reach 89% mean Average Precision index of the feature extraction network software weights. This MWIR photovoltaic detector, with its versatile functionalities, holds significant promise for applications in advanced infrared object detection and recognition systems.

Achieving high accuracy in meniscus tear detection using advanced deep learning models with a relatively small data set.

This study aims to evaluate the effectiveness of advanced deep learning models, specifically YOLOv8 and EfficientNetV2, in detecting meniscal tears on magnetic resonance imaging (MRI)using a relatively small data set. Our data set consisted of MRIstudies from 642 knees-two orthopaedic surgeons labelled and annotated the MR images. The training pipeline included MRI scans of these knees. It was divided into two stages: initially, a deep learning algorithm called YOLO was employed to identify the meniscus location, and subsequently, the EfficientNetV2 deep learning architecture was utilized to detect meniscal tears. A concise report indicating the location and detection of a torn meniscus is provided at the end. The YOLOv8 model achieved mean average precision at 50% threshold (mAP@50) scores of 0.98 in the sagittal view and 0.985 in the coronal view. Similarly, the EfficientNetV2 model obtained area under the curve scores of 0.97 and 0.98 in the sagittal and coronal views, respectively. These outstanding results demonstrate exceptional performance in meniscus localization and tear detection. Despite a relatively small data set, state-of-the-art models like YOLOv8 and EfficientNetV2 yielded promising results. This artificial intelligence system enhances meniscal injury diagnosis by generating instant structured reports, facilitating faster image interpretationand reducing physician workload. Level III.

A High-Precision Human Fall Detection Model Based on FasterNet and Deformable Convolution

To address the challenges of low accuracy and suboptimal real-time performance in fall detection, caused by lighting variations, occlusions, and complex human poses, a novel fall detection algorithm, FDT-YOLO, has been developed. This algorithm builds upon an improved YOLOv8 framework, featuring significant modifications for improved performance. The C2f module in the backbone network has been replaced with the FasterNet module. This substitution enhances feature reuse effectively and reduces computational complexity. Additionally, a deformable convolution module has been added to the neck section. This helps to decrease missed and false detections significantly, which are often caused by dramatic changes in fall poses. Furthermore, the triplet attention mechanism has been incorporated during multi-scale fusion. This mechanism effectively suppresses background interference, focusing more on the target area, thereby improving detection accuracy and robustness. Experimental results have demonstrated that improvements in FDT-YOLO lead to notable enhancements. The mean Average Precision (mAP) at an Intersection over Union (IoU) threshold of 0.5 has been increased from 94.9% to 96.2%. The mAP for the range of 0.5 to 0.95 has been raised from 84.2% to 85.9%. Additionally, the parameter count has been reduced to 9.9 million, which not only enhances detection accuracy but also significantly reduces the rate of false detections.

A Novel Attention-Based Generalized Efficient Layer Aggregation Network for Landslide Detection from Satellite Data in the Higher Himalayas, Nepal

Landslide event detection poses a significant challenge in the remote sensing community, especially with the advancements in computer vision technology. As computational capabilities continue to grow, the traditional manual and partially automated methods of landslide recognition from remote sensing data are transitioning towards automatic approaches using deep learning algorithms. Moreover, attention models, encouraged by the human visual system, have emerged as crucial modules in diverse applications including natural hazard assessment. Therefore, we suggest a novel and intelligent generalized efficient layer aggregation network (GELAN) based on two prevalent attention modules, efficient channel attention (ECA) and convolutional block attention module (CBAM), to enrich landslide detection techniques from satellite images. CBAM and ECA are separately integrated into GELAN at different locations. The experiments are conducted using satellite images of the Nepal Himalayan region. Standard metrics such as precision, recall, F-score, and mAP (mean average precision) are considered for quantitative evaluation. GELANc+CBAM (F-score = 81.5%) demonstrates the best performance. This study underscores the suitability of the proposed approach in up-to-date inventory creation and accurate landslide mapping for disaster recovery and response efforts. Moreover, it contributes to developing early prediction models for landslide hazards.

Object detection based deinterleaving of radar signals using deep learning for cognitive EW

In a real-world environment, multifunction radars (MFRs) pose major challenges to the electronic support system that is a part of cognitive electronic warfare. One of the main problems is deinterleaving of signals belonging to MFRs. The ability of MFRs to change their carrier frequency, pulse width, and pulse repetition interval (PRI) from pulse to pulse makes the deinterleaving task challenging. In this paper, an object detection based deinterleaving approach exploiting amplitude patterns caused by radar beam motions, which are determined based on radar antenna scan types, is proposed to deinterleave MFR signals. Amplitude patterns are created in two-dimensional images using amplitude (AMP) and time of arrival (TOA) parameters obtained from radar pulses. Deinterleaving is performed using a deep learning algorithm applied to these images. To the best of the authors’ knowledge, object detection based deinterleaving of radar signals using AMP-TOA images has not been considered so far. Contrary to the common approaches, in which searching for PRI patterns is required, amplitude patterns formed by the radar beam motions on the electronic support system are used in the proposed method. This enables robust identification of signals of MFRs having PRI, carrier frequency, and pulse width agility. With the proposed method, the intention of the radar, i.e., search or tracking, can be acquired in the deinterleaving stage, which ensures earlier situational awareness. The performance of the method is evaluated for varying number of radar signals from one to five through simulations, in which scenarios with missing pulses at different rates are considered. Simulation results demonstrate that, on the average, more than 0.98 mean average precision (mAP50) is achieved at 30% missing pulse rate. The performance of the method for search radar signals is slightly lower compared to that achieved for tracking radar signals due to the lower number of pulses received by the system. However, more than 0.93 AP50 is achieved for search radar signals in the presence of five radar signals with different missing pulse rates. Besides, real-time performance can be achieved using the proposed method on the GPU platform.

ASD-YOLO: An aircraft surface defects detection method using deformable convolution and attention mechanism

Aircraft surface defect (ASD) detection is crucial for ensuring flight safety. Addressing challenges such as large-scale variations, irregular shapes, and sample imbalance in ASD detection, this paper proposes a ASD-YOLO network based on YOLOv5. ASD-YOLO incorporates several enhancements to improve recognition capabilities. Firstly, a new deformable convolutional feature extraction module (DCNC3) is designed to better learn defects of different shapes, which is combined with a global attention mechanism (GAM) to pay more attention to defects region information. Secondly, the feature representation of small defects is bolstered by the contextual enhancement module (CEM). Lastly, to alleviate sample imbalance problem, we introduce an exponential sliding average weight function (EMA-Slide). Experimental results on two datasets show improvements in mean Average Precision (mAP) by 5.7% and 3.4%, respectively, surpassing mainstream algorithms and offering a novel approach to ASD detection.

Deep Learning Assisted Classification of T1ρ-MR Based Intervertebral Disc Degeneration Phases.

According to the T1ρ value of nucleus pulposus, our previous study has found that intervertebral disc degeneration (IDD) can be divided into three phases based on T1ρ-MR, which is helpful for the selection of biomaterial treatment timing. However, the routine MR sequences for patients with IDD are T1- and T2-MR, T1ρ-MR is not commonly used due to long scanning time and extra expenses, which limits the application of T1ρ-MR based IDD phases. To build a deep learning model to achieve the classification of T1ρ-MR based IDD phases from routine T1-MR images. Retrospective. Sixty (M/F: 35/25) patients with low back pain or lower limb radiculopathy are randomly divided into training (N = 50) and test (N = 10) sets. 1.5 T MR scanner; T1-, T2-, and T1ρ-MR sequence (spin echo). The T1ρ values of the nucleus pulposus in intervertebral discs (IVDs) were measured. IVDs were divided into three phases based on the mean T1ρ value: pre-degeneration phase (mean T1ρ value >110 msec), rapid degeneration phase (mean T1ρ value: 80-110 msec), and late degeneration phase (mean T1ρ value <80 msec). After measurement, the T1ρ values, phases, and levels of IVDs were input into the model as labels. Intraclass correlation coefficient, area under the receiver operating characteristic curve (AUC), F1-score, accuracy, precision, and recall (P < 0.05 was considered significant). In the test dataset, the model achieved a mean average precision of 0.996 for detecting IVD levels. The diagnostic accuracy of the T1ρ-MR based IDD phases was 0.840 and the AUC was 0.871, the average AUC of 5-folds cross validation was 0.843. The proposed deep learning model achieved the classification of T1ρ-MR based IDD phases from routine T1-MR images, which may provide a method to facilitate the application of T1ρ-MR in IDD. 4 TECHNICAL EFFICACY: Stage 2.

Unmanned Aerial Vehicle Object Detection Based on Information-Preserving and Fine-Grained Feature Aggregation

General deep learning methods achieve high-level semantic feature representation by aggregating hierarchical features, which performs well in object detection tasks. However, issues arise with general deep learning methods in UAV-based remote sensing image object detection tasks. Firstly, general feature aggregation methods such as stride convolution may lead to information loss in input samples. Secondly, common FPN methods introduce conflicting information by directly fusing feature maps from different levels. These shortcomings limit the model’s detection performance on small and weak targets in remote sensing images. In response to these concerns, we propose an unmanned aerial vehicle (UAV) object detection algorithm, IF-YOLO. Specifically, our algorithm leverages the Information-Preserving Feature Aggregation (IPFA) module to construct semantic feature representations while preserving the intrinsic features of small objects. Furthermore, to filter out irrelevant information introduced by direct fusion, we introduce the Conflict Information Suppression Feature Fusion Module (CSFM) to improve the feature fusion approach. Additionally, the Fine-Grained Aggregation Feature Pyramid Network (FGAFPN) facilitates interaction between feature maps at different levels, reducing the generation of conflicting information during multi-scale feature fusion. The experimental results on the VisDrone2019 dataset demonstrate that in contrast to the standard YOLOv8-s, our enhanced algorithm achieves a mean average precision (mAP) of 47.3%, with precision and recall rates enhanced by 6.3% and 5.6%, respectively.

Deep learning application of vertebral compression fracture detection using mask R-CNN

Vertebral compression fractures (VCFs) of the thoracolumbar spine are commonly caused by osteoporosis or result from traumatic events. Early diagnosis of vertebral compression fractures can prevent further damage to patients. When assessing these fractures, plain radiographs are used as the primary diagnostic modality. In this study, we developed a deep learning based fracture detection model that could be used as a tool for primary care in the orthopedic department. We constructed a VCF dataset using 487 lateral radiographs, which included 598 fractures in the L1-T11 vertebra. For detecting VCFs, Mask R-CNN model was trained and optimized, and was compared to three other popular models on instance segmentation, Cascade Mask R-CNN, YOLOACT, and YOLOv5. With Mask R-CNN we achieved highest mean average precision score of 0.58, and were able to locate each fracture pixel-wise. In addition, the model showed high overall sensitivity, specificity, and accuracy, indicating that it detected fractures accurately and without misdiagnosis. Our model can be a potential tool for detecting VCFs from a simple radiograph and assisting doctors in making appropriate decisions in initial diagnosis.

Image generation of hazardous situations in construction sites using text-to-image generative model for training deep neural networks

There has been a persistent challenge in acquiring sufficient training image data for deep neural networks (DNNs) to enhance safety monitoring on construction sites. Given the prevalence of textual data in the construction sector and the capabilities of multi-modal AI systems, this paper presents the use of text-to-image models to generate training images that capture the relationships between objects involved in construction accidents. Through a systematic prompt design process, a synthetic dataset of 3585 images across 27 hazardous scenarios was generated. The efficacy of this method is demonstrated by the performance of DNN models trained on these virtual images, which achieved a mean Average Precision (mAP) of approximately 64% in object detection and 60% in segmentation tasks. This paper demonstrates the potential of text-to-image models in mitigating the scarcity of training data and enhancing the capability of DNNs to identify potential hazards.