Average Precision Values Research Articles

Multi-granularity tooth analysis via YOLO-based object detection models for effective tooth detection and classification

Accurate detection and classification of teeth is the first step in dental disease diagnosis. However, the same class of tooth exhibits significant variations in surface appearance. Moreover, the complex geometrical structure poses challenges in learning discriminative features among the different tooth classes. Due to these complex features, tooth classification is one of the challenging research domains in deep learning. To address the aforementioned issues, the presented study proposes discriminative local feature extraction at different granular levels using YOLO models. However, this necessitates a granular intra-oral image dataset. To facilitate this requirement, a dataset at three granular levels (two, four, and seven teeth classes) is developed. YOLOv5, YOLOv6, and YOLOv7 models were trained using 2,790 images. The results indicate superior performance of YOLOv6 for two-class classification problems. The model generated a mean average precision (mAP) value of 94%. However, as the granularity level is increased, the performance of YOLO models decreases. For, four and seven-class classification problems, the highest mAP value of 87% and 79% was achieved by YOLOv5 respectively. The results indicate that different levels of granularity play an important role in tooth detection and classification. The YOLO’s performance gradually decreased as the granularity decreased especially at the finest granular level.

Computer-vision-based artificial intelligence for detection and recognition of instruments and organs during radical laparoscopic gastrectomy for gastric cancer: a multicenter study

Objective: To investigate the feasibility and accuracy of computer vision-based artificial intelligence technology in detecting and recognizing instruments and organs in the scenario of radical laparoscopic gastrectomy for gastric cancer. Methods: Eight complete laparoscopic distal radical gastrectomy surgery videos were collected from four large tertiary hospitals in China (First Medical Center of Chinese PLA General Hospital [three cases], Liaoning Cancer Hospital [two cases], Liyang Branch of Jiangsu Province People's Hospital [two cases], and Fudan University Shanghai Cancer Center [one case]). PR software was used to extract frames every 5-10 seconds and convert them into image frames. To ensure quality, deduplication was performed manually to remove obvious duplication and blurred image frames. After conversion and deduplication, there were 3369 frame images with a resolution of 1,920×1,080 PPI. LabelMe was used for instance segmentation of the images into the following 23 categories: veins, arteries, sutures, needle holders, ultrasonic knives, suction devices, bleeding, colon, forceps, gallbladder, small gauze, Hem-o-lok, Hem-o-lok appliers, electrocautery hooks, small intestine, hepatogastric ligaments, liver, omentum, pancreas, spleen, surgical staplers, stomach, and trocars. The frame images were randomly allocated to training and validation sets in a 9:1 ratio. The YOLOv8 deep learning framework was used for model training and validation. Precision, recall, average precision (AP), and mean average precision (mAP) were used to evaluate detection and recognition accuracy. Results: The training set contained 3032 frame images comprising 30 895 instance segmentation counts across 23 categories. The validation set contained 337 frame images comprising 3407 instance segmentation counts. The YOLOv8m model was used for training. The loss curve of the training set showed a smooth gradual decrease in loss value as the number of iteration calculations increased. In the training set, the AP values of all 23 categories were above 0.90, with a mAP of 0.99, whereas in the validation set, the mAP of the 23 categories was 0.82. As to individual categories, the AP values for ultrasonic knives, needle holders, forceps, gallbladders, small pieces of gauze, and surgical staplers were 0.96, 0.94, 0.91, 0.91, 0.91, and 0.91, respectively. The model successfully inferred and applied to a 5-minutes video segment of laparoscopic gastroenterostomy suturing. Conclusion: The primary finding of this multicenter study is that computer vision can efficiently, accurately, and in real-time detect organs and instruments in various scenarios of radical laparoscopic gastrectomy for gastric cancer.

Real-time detection of plastic part surface defects using deep learning- based object detection model

In this study, it was aimed to detect defects in plastic parts produced in a company operating in the automotive sub-industry using the YOLOv8 object detection model. The defect types seen in plastic parts were evaluated with the help of Pareto analysis, and scratches, stains and shine were selected as the most common defect types, and data on the three defect types were collected. YOLOv8 models were trained using faulty part images. As a result of the training, the highest mean average precision value of 0.990 was obtained in the YOLOv8s model, and the shortest training time was obtained in the YOLOv8n model. In the YOLOv8s model, which gave the highest mAP value, hyperparameter adjustment was made according to the batch size and learning rate values. The testing phase was carried out with the hyperparameter values that gave the best results and the mAP value was obtained as 0.902.

Intelligent Detection of Muskmelon Ripeness in Greenhouse Environment Based on YOLO-RFEW

Accurate detection of muskmelon fruit ripeness is crucial to ensure fruit quality, optimize picking time, and enhance economic benefits. This study proposes an improved lightweight YOLO-RFEW model based on YOLOv8n, aiming to address the challenges of low efficiency in muskmelon fruit ripeness detection and the complexity of deploying a target detection model to a muskmelon picking robot. Firstly, the RFAConv replaces the Conv in the backbone part of YOLOv8n, allowing the network to focus more on regions with significant contributions in feature extraction. Secondly, the feature extraction and fusion capability are enhanced by improving the C2f module into a C2f-FE module based on FasterNet and an Efficient Multi-Scale attention (EMA) mechanism within the lightweight model. Finally, Weighted Intersection over Union (WIoU) is optimized as the loss function to improve target frame prediction capability and enhance target detection accuracy. The experimental results demonstrate that the YOLO-RFEW model achieves high accuracy, with precision, recall, F1 score, and mean Average Precision (mAP) values of 93.16%, 83.22%, 87.91%, and 90.82%, respectively. Moreover, it maintains a lightweight design and high efficiency with a model size of 4.75 MB and an inference time of 1.5 ms. Additionally, in the two types of maturity tests (M-u and M-r), APs of 87.70% and 93.94% are obtained, respectively, by the YOLO-RFEW model. Compared to YOLOv8n, significant improvements in detection accuracy have been achieved while reducing both model size and computational complexity using the proposed approach for muskmelon picking robots’ real-time detection requirements. Furthermore, when compared to lightweight models such as YOLOv3-Tiny, YOLOv4-Tiny, YOLOv5s, YOLOv7-Tiny, YOLOv8s, and YOLOv8n, the YOLO-RFEW model demonstrates superior performance with only 28.55%, 22.42%, 24.50%, 40.56%, 22.12%, and 79.83% of their respective model sizes, respectively, while achieving the highest F1 score and mAP values among these seven models. The feasibility and effectiveness of our improved scheme are verified through comparisons between thermograms generated by YOLOv8n and YOLO-RFEW as well as detection images. In summary, the YOLO-RFEW model not only improves the accuracy rate of muskmelon ripeness detection but also successfully realizes the lightweight and efficient performance, which has important theoretical support and application value in the field of muskmelon picking robot development.

Constructing and applying a neural-network-based architectural landscape evaluation model

With the continuous improvement of living standards, people go outdoors and spend more and more time in scenic spots. The landscape architecture design that serves people in urban scenic spots attracts more and more public attention, which puts forward higher requirements for landscape architecture design that serves people in scenic spots. How to integrate better the design of all kinds of landscape architecture into nature, to serve the public better, is an urgent problem to be solved at this stage. This paper selects the evaluation indexes of urban architectural landscapes, uses the analytic hierarchy process to determine the weight of each index and quantifies six evaluation indexes to build an evaluation model of architectural landscape design. In terms of the improvement of the you only look once version 4 (YOLOv4) model, MobileNetV3 was selected as the backbone feature extraction network, and the convolution in the feature enhancement extraction network was replaced by the depth-separable volume, and an architectural landscape recognition system based on the improved YOLOv4 model was constructed. In terms of algorithm performance verification, the improved algorithm was compared with the single-shot detector, MobileNetV3, ShuffleNetV2, YOLOv3, YOLOv4 and YOLOv5s algorithms under multiple evaluation indexes. The experimental results show that the size of the model is 51.4 MB, which does not cause a large burden. The mean average precision value of the improved YOLOv4 algorithm is 93.5%, and the frames per second (FPS) value is 30 FPS, which has higher recognition accuracy and detection speed and has obvious advantages.

A Detection Transformer-Based Intelligent Identification Method for Multiple Types of Road Traffic Safety Facilities.

Road traffic safety facilities (TSFs) are of significant importance in the management and maintenance of traffic safety. The complexity and variety of TSFs make it challenging to detect them manually, which renders the work unsustainable. To achieve the objective of automatic TSF detection, a target detection dataset, designated TSF-CQU (TSF data collected by Chongqing University), was constructed based on images collected by a car recorder. This dataset comprises six types of TSFs and 8410 instance samples. A detection transformer with an improved denoising anchor box (DINO) was selected to construct a model that would be suitable for this scenario. For comparison purposes, Faster R-CNN (Region Convolutional Neural Network) and Yolov7 (You Only Look Once version 7) were employed. The DINO model demonstrated the highest performance on the TSF-CQU dataset, with a mean average precision (mAP) of 82.2%. All of the average precision (AP) values exceeded 0.8, except for streetlights (AP = 0.77) and rods (AP = 0.648). The DINO model exhibits minimal instances of erroneous recognition, which substantiates the efficacy of the contrastive denoising training approach. The DINO model rarely makes misjudgments, but a few missed detection.

A real-time surface defects detection model via dual-branch feature extraction and dynamic multi-scale fusion attention

Surface defect detection is a challenging task in industrial manufacturing, and the detection method based on deep learning has become the mainstream trend in the industry. However, the task of detecting defects on transparent plastic bottles poses unique challenges due to their clear, smooth surfaces and minimal texture, which contribute to specular reflections and make small, low-contrast defects difficult to discern. To tackle these challenges, we introduce the BiD-YOLO framework, an advanced version of the YOLOv5 model, tailored for real-time surface defect detection on such substrates. This framework notably enhances the detection accuracy for small, low-contrast defects and minimizes miss rates. At its core, BiD-YOLO incorporates a dual-branch feature extractor (DBFE) that utilizes both standard, dilated convolutions and a specialized small-object feature extraction branch to capture a broad spectrum of contextual information, optimizing the detection of fine details. Additionally, the dynamic multi-scale pyramid fusion attention (DyMFA) block with coordinate attention (CA) effectively addresses the loss of information in small-scale defects—a typical shortfall in conventional attention mechanisms—thereby improving detection precision across both channel and spatial dimensions. To achieve an optimal balance between accuracy and computational efficiency, we introduce two versions of the dynamic multi-scale pyramid attention block: multi-scale pyramid channel attention and dynamic channel attention. We also curated and annotated the TPSD dataset, a specialized collection of images showcasing surface defects on transparent plastic bottles under diverse real-world production conditions. Together with the NEU-DET dataset, these resources were employed to validate the BiD-YOLO model's effectiveness. Experimental results demonstrate a substantial improvement in defect detection capabilities, achieving mean average precision (mAP) values of 63.1% and 85.6%, respectively. Moreover, the two working models exhibit FPS values of 47.23FPS and 50.21FPS respectively. These findings underscore the BiD-YOLO model's pivotal role in reducing oversight in defect detection, thereby enhancing quality control within industrial manufacturing environments. The BiD-YOLO framework represents a significant advancement in the automated detection of surface defects on transparent plastic bottles, merging innovative technical features with robust practical applicability for industrial use.

Analisis Perbandingan Klasifikasi Penyakit Jantung Menggunakan Algoritma Nai ̈ve Bayes dan Algoritma Logistic Regression

Heart disease is a condition where parts of the heart are damaged. Thus, early detection is needed. One of them is by doing data mining classification using the Naïve Bayes and Logistic Regression algorithms. This research will compare Naïve Bayes and Logistic Regression algorithms through the training percentage split and k-fold cross validation methods to get the best classification results in detecting heart disease by calculating the average value of precision, recall, and accuracy. The Naïve Bayes algorithm with the training percentage split method produces average values for precision, recall, and accuracy of 83%, 82.5% and 81%, while the Naïve Bayes algorithm with k-fold cross validation provides average values for precision, recall, and accuracy of 83.5%, 85.5% and 83%. Logistic Regression algorithm with percentage split training method produces average values for precision, recall, and accuracy of 73.5%, 73.5% and 73%, while Logistic Regression algorithm using k-fold cross validation produces average values for precision, recall, and accuracy of 84%, 83.5% and 84%. This shows that the Naïve Bayes algorithm using percentage split is better than Logistic Regression, but when using the k-fold cross validation method, the Logistic Regression algorithm has a significant increase compared to Naïve Bayes. So that to classify heart disease is better with the Logistic Regression Algorithm with the k-fold cross validation method.

AI-Assisted Detection of Interproximal, Occlusal, and Secondary Caries on Bite-Wing Radiographs: A Single-Shot Deep Learning Approach.

Tooth decay is a common oral disease worldwide, but errors in diagnosis can often be made in dental clinics, which can lead to a delay in treatment. This study aims to use artificial intelligence (AI) for the automated detection and localization of secondary, occlusal, and interproximal (D1, D2, D3) caries types on bite-wing radiographs. The eight hundredand sixty bite-wing radiographs were collected from the School of Dentistry database. Pre-processing and data augmentation operations were performed. Interproximal (D1, D2, D3), secondary, and occlusal caries on bite-wing radiographs were annotated by two oral radiologists. The data were split into 80% for training, 10% for validation, and 10% for testing. The AI-based training process was conducted using the YOLOv8 algorithm. A clinical decision support system interface was designed using the Python PyQT5 library, allowing for the use of dental caries detection without the need for complex programming procedures. In the test images, the average precision, average sensitivity, and average F1 score values for secondary, occlusal, and interproximal caries were obtained as 0.977, 0.932, and 0.954, respectively. The AI-based dental caries detection system yielded highly successful results in the test, receiving full approval from dentists for clinical use. YOLOv8 has the potential to increase sensitivity and reliability while reducing the burden on dentists and can prevent diagnostic errors in dental clinics.

Query Expansion Using Proposed Location-Based Algorithm for Hindi–English CLIR: Analyzing Three Test Collections

The rapid growth of contents on the Web in different languages increases the demand of Cross-Lingual Information Retrieval (CLIR). The accuracy of result suffers due to many problems such as ambiguity and drift issue in query. Query Expansion (QE) offers reliable solution for obtaining suitable documents for user queries. In this paper, we proposed an architecture for Hindi–English CLIR system using QE for improving the relevancy of retrieved results. In this architecture, for the addition of term(s) at appropriate position(s), we proposed a location-based algorithm to resolve the drift query issue in QE. User queries in Hindi language have been translated into document language (i.e. English) and the accuracy of translation is improved using Back-Translation. Google search has been performed and the retrieved documents are ranked using Okapi BM25 to arrange the documents in the order of decreasing relevancy to select the most suitable terms for QE. We used term selection value (TSV) for QE and for retrieving the terms, we created three test collections namely the (i) description and narration of the Forum for Information Retrieval Evaluation (FIRE) dataset, (ii) Snippets of retrieved documents against each query and (iii) Nearest-Neighborhood (NN) words against each query word among the ranked documents. To evaluate the system, 50 queries of Hindi language are selected from the FIRE-2012 dataset. In this paper, we performed two experiments: (i) impact of the proposed location-based algorithm on the proposed architecture of CLIR; and (ii) analysis of QE using three datasets, i.e. FIRE, NN and Snippets. In the first case, result shows that the relevancy of Hindi–English CLIR is improved by performing QE using the location-based algorithm and a 12% of improvement is achieved as compared to the results of QE obtained without applying the location-based algorithm. In the second case, the location-based algorithm is applied on three datasets. The Mean Average Precision (MAP) values of retrieved documents after QE are 0.5379 (NN), 0.6018 (FIRE) and 0.6406 (Snippets) for the three test collections, whereas the MAP before QE is 0.37102. This clearly shows the significant improvement of retrieved results for all three test collections. Among the three test collections, QE has been found most effective along with Snippets as indicated by the results with the improvements of 6.48% and 19.12% over FIRE and NN test collections, respectively.

Research on Bearing Surface Scratch Detection Based on Improved YOLOV5.

Bearings are crucial components of machinery and equipment, and it is essential to inspect them thoroughly to ensure a high pass rate. Currently, bearing scratch detection is primarily carried out manually, which cannot meet industrial demands. This study presents research on the detection of bearing surface scratches. An improved YOLOV5 network, named YOLOV5-CDG, is proposed for detecting bearing surface defects using scratch images as targets. The YOLOV5-CDG model is based on the YOLOV5 network model with the addition of a Coordinate Attention (CA) mechanism module, fusion of Deformable Convolutional Networks (DCNs), and a combination with the GhostNet lightweight network. To achieve bearing surface scratch detection, a machine vision-based bearing surface scratch sensor system is established, and a self-made bearing surface scratch dataset is produced as the basis. The scratch detection final Average Precision (AP) value is 97%, which is 3.4% higher than that of YOLOV5. Additionally, the model has an accuracy of 99.46% for detecting defective and qualified products. The average detection time per image is 263.4 ms on the CPU device and 12.2 ms on the GPU device, demonstrating excellent performance in terms of both speed and accuracy. Furthermore, this study analyzes and compares the detection results of various models, demonstrating that the proposed method satisfies the requirements for detecting scratches on bearing surfaces in industrial settings.

Seedling-YOLO: High-Efficiency Target Detection Algorithm for Field Broccoli Seedling Transplanting Quality Based on YOLOv7-Tiny

The rapid and accurate detection of broccoli seedling planting quality is crucial for the implementation of robotic intelligent field management. However, existing algorithms often face issues of false detections and missed detections when identifying the categories of broccoli planting quality. For instance, the similarity between the features of broccoli root balls and soil, along with the potential for being obscured by leaves, leads to false detections of “exposed seedlings”. Additionally, features left by the end effector resemble the background, making the detection of the “missed hills” category challenging. Moreover, existing algorithms require substantial computational resources and memory. To address these challenges, we developed Seedling-YOLO, a deep-learning model dedicated to the visual detection of broccoli planting quality. Initially, we designed a new module, the Efficient Layer Aggregation Networks-Pconv (ELAN_P), utilizing partial convolution (Pconv). This module serves as the backbone feature extraction network, effectively reducing redundant calculations. Furthermore, the model incorporates the Content-aware ReAssembly of Features (CARAFE) and Coordinate Attention (CA), enhancing its focus on the long-range spatial information of challenging-to-detect samples. Experimental results demonstrate that our Seedling-YOLO model outperforms YOLOv4-tiny, YOLOv5s, YOLOv7-tiny, and YOLOv7 in terms of speed and precision, particularly in detecting ‘exposed seedlings’ and ‘missed hills’-key categories impacting yield, with Average Precision (AP) values of 94.2% and 92.2%, respectively. The model achieved a mean Average Precision of 0.5 (mAP@0.5) of 94.3% and a frame rate of 29.7 frames per second (FPS). In field tests conducted with double-row vegetable ridges at a plant spacing of 0.4 m and robot speed of 0.6 m/s, Seedling-YOLO exhibited optimal efficiency and precision. It achieved an actual detection precision of 93% and a detection efficiency of 180 plants/min, meeting the requirements for real-time and precise detection. This model can be deployed on seedling replenishment robots, providing a visual solution for robots, thereby enhancing vegetable yield.

PARDet: Dynamic point set alignment for rotated object detection

Due to the inherent mismatch between rotated objects and horizontal features, feature point misalignment has been a challenge in the task of Rotated Object Detection (ROD). Specifically, considering the pattern of convolution, foreground features are often mixed with background noise, which can confuse the model and affect the model from feature point alignment during the training phase. To mitigate this issue, previous methods concentrate on fixed positions derived from predicted boxes by additionally introducing a refinement stage. However, merely learning fixed position priors during training can result in suboptimal alignment and inefficiency during inference. This paper introduces a dynamic point alignment detector to concurrently address issues associated with feature misalignment and inference inefficiency. The method is made up of two components: the fine-grained points generator (FPG) captures key information, and the point alignment module (PAM) derives precise feature representations. Both modules empower the detector with the capability to dynamically perceive rotated objects, extracting more comprehensive and reasoned feature contents from the feature maps. In general, our method enables the model to independently identify and prioritize the valuable features during the training process. Subsequently, during the inference stage, the results can be directly predicted without additional alignment operations. The experimental results demonstrate that our method can achieve competitive and superior results with average precision (AP) values of 79.33%, 95.73%, and 63.37% on the DOTA, HRSC2016, and DIOR-R datasets, respectively. Codes will be publicly available at https://github.com/Xuyihaoby/PARDet.

Large Span Sizes and Irregular Shapes Target Detection Methods Using Variable Convolution-Improved YOLOv8.

In this work, an object detection method using variable convolution-improved YOLOv8 is proposed to solve the problem of low accuracy and low efficiency in detecting spanning and irregularly shaped samples. Aiming at the problems of the irregular shape of a target, the low resolution of labeling frames, dense distribution, and the ease of overlap, a deformable convolution module is added to the original backbone network. This allows the model to deal flexibly with the problem of the insufficient perceptual field of the target corresponding to the detection point, and the situations of leakage and misdetection can be effectively improved. In order to solve the issue that small target detection is susceptible to image background and noise interference, the Sim-AM (simple parameter-free attention mechanism) module is added to the backbone network of YOLOv8, which enhances the attention to the underlying features and, thus, improves the detection accuracy of the model. More importantly, the Sim-AM module does not need to add parameters to the original network, which reduces the computation of the model. To address the problem of complex model structures that can lead to slower detection, the spatial pyramid pooling of the backbone network is replaced with focal modulation networks, which greatly simplifies the computation process. The experimental validation was carried out on the scrap steel dataset containing a large number of targets of multiple shapes and sizes. The results showed that the improved YOLOv8 network model improves the AP (average precision) by 2.1%, the mAP (mean average precision value) by 0.8%, and reduces the FPS (frames per second) by 5.4, which meets the performance requirements of real-time industrial inspection.

Classification of peanut pod rot based on improved YOLOv5s.

Peanut pod rot is one of the major plant diseases affecting peanut production and quality over China, which causes large productivity losses and is challenging to control. To improve the disease resistance of peanuts, breeding is one significant strategy. Crucial preventative and management measures include grading peanut pod rot and screening high-contributed genes that are highly resistant to pod rot should be carried out. A machine vision-based grading approach for individual cases of peanut pod rot was proposed in this study, which avoids time-consuming, labor-intensive, and inaccurate manual categorization and provides dependable technical assistance for breeding studies and peanut pod rot resistance. The Shuffle Attention module has been added to the YOLOv5s (You Only Look Once version 5 small) feature extraction backbone network to overcome occlusion, overlap, and adhesions in complex backgrounds. Additionally, to reduce missing and false identification of peanut pods, the loss function CIoU (Complete Intersection over Union) was replaced with EIoU (Enhanced Intersection over Union). The recognition results can be further improved by introducing grade classification module, which can read the information from the identified RGB images and output data like numbers of non-rotted and rotten peanut pods, the rotten pod rate, and the pod rot grade. The Precision value of the improved YOLOv5s reached 93.8%, which was 7.8%, 8.4%, and 7.3% higher than YOLOv5s, YOLOv8n, and YOLOv8s, respectively; the mAP (mean Average Precision) value was 92.4%, which increased by 6.7%, 7.7%, and 6.5%, respectively. Improved YOLOv5s has an average improvement of 6.26% over YOLOv5s in terms of recognition accuracy: that was 95.7% for non-rotted peanut pods and 90.8% for rotten peanut pods. This article presented a machine vision- based grade classification method for peanut pod rot, which offered technological guidance for selecting high-quality cultivars with high resistance to pod rot in peanut.

Enhanced YOLO v3 for precise detection of apparent damage on bridges amidst complex backgrounds

A bridge disease identification approach based on an enhanced YOLO v3 algorithm is suggested to increase the accuracy of apparent disease detection of concrete bridges under complex backgrounds. First, the YOLO v3 network structure is enhanced to better accommodate the dense distribution and large variation of disease scale characteristics, and the detection layer incorporates the squeeze and excitation (SE) networks attention mechanism module and spatial pyramid pooling module to strengthen the semantic feature extraction ability. Secondly, CIoU with better localization ability is selected as the loss function for training. Finally, the K-means algorithm is used for anchor frame clustering on the bridge surface disease defects dataset. 1363 datasets containing exposed reinforcement, spalling, and water erosion damage of bridges are produced, and network training is done after manual labelling and data improvement in order to test the efficacy of the algorithm described in this paper. According to the trial results, the YOLO v3 model has enhanced more than the original model in terms of precision rate, recall rate, Average Precision (AP), and other indicators. Its overall mean Average Precision (mAP) value has also grown by 5.5%. With the RTX2080Ti graphics card, the detection frame rate increases to 84 Frames Per Second, enabling more precise and real-time bridge illness detection.

DBH-YOLO: a surgical instrument detection method based on feature separation in laparoscopic surgery.

Accurately locating and analysing surgical instruments in laparoscopic surgical videos can assist doctors in postoperative quality assessment. This can provide patients with more scientific and rational solutions for healing surgical complications. Therefore, we propose an end-to-end algorithm for the detection of surgical instruments. Dual-Branched Head (DBH) and Overall Intersection over Union Loss (OIoU Loss) are introduced to solve the problem of inaccurate surgical instrument detection, both in terms of localization and classification. An effective method (DBHYOLO) for the detection for laparoscopic surgery in complex scenarios is proposed. This study manually annotates a new laparoscopic gastric cancer resection surgical instrument location dataset LGIL, which provides a better validation platform for surgical instrument detection methods. The proposed method's performance was tested using the m2cai16-tool-locations, LGIL, and Onyeogulu datasets. The mean Average Precision (mAP) values obtained were 96.8%, 95.6%, and 98.4%, respectively, which were higher than the other classical models compared. The improved model is more effective than the benchmark network in distinguishing between surgical instrument classes with high similarity and avoiding too many missed detection cases. In this paper, the problem of inaccurate detection of surgical instruments is addressed from two different perspectives: classification and localization. And the experimental results on three representative datasets verify the performance of DBH-YOLO. It is shown that this method has a good generalization capability.

An IoT‐based multiple teaching quality evaluation method for English translation with improved deep learning

AbstractTo enhance the teaching quality (TQ) of English translation (ET) courses, multivariate evaluation methods have garnered significant attention for their ability to identify deficiencies in the teaching process and subsequently improve instructional standards. Traditional evaluation techniques have shown limited effectiveness. Therefore, this paper proposes an ET in multiple teaching quality (MTQ) evaluation method with improved deep learning in internet of things (IoT). First, the paper establishes evaluation indicators for ET in MTQ, which mainly encompass ET teaching effectiveness, pedagogic competency in ET, teaching methods, content, as well as attitudes towards ET teaching. It then utilizes IoT technology to preliminarily collect data on these indicators, and using clustering algorithm based on weighted attributes and density (CABWAD) algorithm to mine data on English teaching MTQ evaluation indicators for ET. The extracted evaluation indicator data is then denoised using a probabilistic undirected graph model. Ultimately, the multilayer perceptron in deep learning is improved through Wolfe line search optimization, and this enhanced multilayer perceptron is employed to construct an ET in MTQ evaluation model. The denoised indicator data is inputted into the model, which then outputs precise MTQ evaluation results. The results show that the absolute value of the average Pearson correlation coefficient of this method is the highest, the Spearman correlation coefficient is the lowest, the mean average precision value is 0.965, and the positive category imbalance degree and the negative category imbalance degree are the lowest, indicating that the proposed method has outstanding performance in all aspects, and has certain application value in the field of TQ evaluation.

Improving efficiency and accuracy of levee hazard detection with deep learning

This paper presents a model framework based on a deep learning algorithm using Faster R-CNN to improve the accuracy and efficiency of detecting long-distance levee hazards. The proposed method aims to assist technicians in identifying hazards in resistivity inversion profiles, thereby reducing the manual workload and extracting valuable information from a large volume of data using deep learning techniques. To this end, we constructed a dataset of levee hazards using inversion images of electrical resistivity imaging data obtained from numerical simulations, indoor experiments, and actual levee hazards. Subsequently, we utilized image augmentation techniques to expand the dataset and enhance the model's performance, resulting in a total of 2000 labeled hazard images. The network was then trained from scratch by setting the hyperparameters. the trained weight parameters and network architecture were saved for future use. The model's performance was evaluated using standard evaluation metrics, including precision, recall, F1 score, and average precision (AP). The proposed model demonstrated robustness and adaptability, achieving high precision and accuracy with an AP value of up to 100%. Furthermore, we validated the method using three cases, and the results indicated its superiority over traditional manual identification-based or outlier analysis detection of levee hazards in practical scenarios. This study emphasizes the significant advantages of deep learning techniques over the traditional methods, including improved accuracy, automation, speed, and scalability. It suggests that intelligent detection based on deep learning can accurately identify and locate hazards in levees.

Magnetic Flux Leakage Defect Identification Method for Small-Diameter Pipeline Elbow Based on the Improved YOLOv5

Abstract The elbow is an important constituent of oil and gas pipeline systems and plays a key role in changing the direction of pipelines. Corrosion defects pose a significant risk to the safe operation of elbows. Magnetic flux leakage (MFL) detection has been developed as a suitable technique for identifying defects in pipelines. To address the distortion of elbow defect signals in the images arising from variations in the liftoff value of the leakage detector, this paper proposed an image identification method based on an improved YOLOv5 network. The differences in defect images are simulated by analyzing the liftoff value of the magnetization unit. A defect image enhancement method of multiscale retinex with color restoration fusion homomorphic filtering (MSRCR-HF) is employed to enhance the features of defective MFL signal images. To further improve the accuracy of the model, the YOLOv5 network is optimized by integrating the convolutional block attention module (CBAM) and the space-to-depth-nonstrided convolution (SPD-Conv) module. The results show that the proposed image enhancement method effectively accentuates the features of defect images. Moreover, the suggested image identification method exhibits superior accuracy in identification. The mean average precision (mAP) values for the original image set and the enhanced image set are 85.0% and 91.4%, respectively. Consequently, the proposed method is shown to be highly viable for the automatic identification of MFL defects in small-diameter pipe elbows.