Automatic Detection Method Research Articles

A deep learning-based detection method for pig body temperature using infrared thermography

Body temperature is one of the important indicators that reflect the health of pigs. The traditional rectal temperature measurement is inconvenient and time-consuming, and also easy to cause stress responses to pigs. Infrared Thermography (ITG) was supposed to have potentials to realize non-invasive and rapid temperature detection for pigs in intensive pig farming. In this paper, an automatic temperature detection method base on ITG was developed. First, temperatures on six regions on pig body surface (i.e., forehead (FH), eyes, nose, ear root (ET), back and anus) were measured by ITG for the region of interest (ROI) selection; Then, an improved model of YOLOv5s-BiFPN was developed for automatic ROI detection and temperature extraction. A dataset with 2797 images that collected from sixteen pigs for 30 days was used for model development. It was shown that temperatures on FH and ET were supposed to be the ROI for ITG temperature detection and because of their strong correlations with the rectal temperature among the six parts on pig body surface. Also, the maximum temperature (MaxT) on FH and ET could reflect pig’s body temperature variations the best. The proposed model of YOLOv5s-BiFPN achieved optimal performances (e.g., the mAP was 96.36%, outperformance was 20 MB, target detection speed was up to 100 frame/s), and the mAPs were increased by 4.85%, 4.38%, 1.60%, 1.56%, 31.52%, and 22.42% compared with models of CenterNet, Faster R-CNN, YOLOv4, YOLOv5s, Nanodet and YOLOv5n, respectively. Therefore, it is a feasible way for pig body temperature automatic detection and facilitates early staged disease warning and environmental control.

Static vulnerability detection based on class separation

Software vulnerability detection is a key step to prevent the system from being attacked. However, tens of thousands of codes have brought great challenges to engineers, so we urgently need an automatic and intelligent vulnerability detection method. The existing vulnerability detection model based on deep learning has the problem that it is difficult to separate the features of vulnerable and neutral code. Based on the code data drive, this paper proposes a static vulnerability detection method SDV(Statically Detecting Vulnerability) for C∖C++ programs. SDV is a function-level vulnerability code detection method. This paper uses a code property graph to represent the code and decouples the feature extractor and the classifier. In the graph feature extraction stage, we use Jump Graph Attention Network layers and convolutional pooling layers. Their combination can not only prevent the over-smoothing problem but also separate the sample classes deeply. Finally, on the chrdeb dataset, SDV outperforms state-of-the-art function-level vulnerability detection methods by 52.3%, 15.9%, and 39.6% in Precision, Recall, and F1-Score, respectively. On the real project sard, the number of vulnerabilities detected by SDV is 10.7 times more than Reveal.

Automatic Identification of Auroral Substorms Based on Ultraviolet Spectrographic Imager Aboard Defense Meteorological Satellite Program (DMSP) Satellite

An auroral substorm is an important physical process of energy accumulation and explosive release in the Earth’s magnetosphere, and is an important research object of space environment monitoring and space weather warnings. A westward traveling surge (WTS) is a typical auroral physical process of an auroral substorm. Its static characteristic is auroral folding at the polar boundary of an auroral oval and its dynamic characteristic is the westward motion of auroral folding. According to the static characteristic of a WTS, we defined a set of feature parameters based on the morphology and designed a set of automatic detection and discrimination methods; that is, the WTS was identified by using the extracted features and pattern recognition approaches. This approach was tested by using the aurora data of the ultraviolet auroral spectral imager of the Defense Meteorological Satellite Program (DMSP) satellite. The results showed that the accuracy rate of automatic recognition was 61.39%~63.61% and the precision rate was 55.52%~57.92%. The experimental results showed that the approach was effective at detecting the typical characteristics of an auroral substorm (WTS).

A study on feature selection using multi-domain feature extraction for automated k-complex detection.

K-complex detection plays a significant role in the field of sleep research. However, manual annotation for electroencephalography (EEG) recordings by visual inspection from experts is time-consuming and subjective. Therefore, there is a necessity to implement automatic detection methods based on classical machine learning algorithms. However, due to the complexity of EEG signal, current feature extraction methods always produce low relevance to k-complex detection, which leads to a great performance loss for the detection. Hence, finding compact yet effective integrated feature vectors becomes a crucially core task in k-complex detection. In this paper, we first extract multi-domain features based on time, spectral analysis, and chaotic theory. Those features are extracted from a 0.5-s EEG segment, which is obtained using the sliding window technique. As a result, a vector containing twenty-two features is obtained to represent each segment. Next, we explore several feature selection methods and compare their performance in detecting k-complex. Based on the analysis of the selected features, we identify compact features which are fewer than twenty-two features and deemed as relevant and proceeded to the next step. Additionally, three classical classifiers are employed to evaluate the performance of the feature selection models. The results demonstrate that combining different features significantly improved the k-complex detection performance. The best performance is achieved by applying the feature selection method, which results in an accuracy of 93.03%7.34, sensitivity of 93.81%5.62%, and specificity 94.135.81, respectively, using a smaller number of the combined feature sets. The proposed method in this study can serve as an efficient tool for the automatic detection of k-complex, which is useful for neurologists or doctors in the diagnosis of sleep research.

Automatic Detection of Brain Metastases in T1-Weighted Construct-Enhanced MRI Using Deep Learning Model.

As a complication of malignant tumors, brain metastasis (BM) seriously threatens patients' survival and quality of life. Accurate detection of BM before determining radiation therapy plans is a paramount task. Due to the small size and heterogeneous number of BMs, their manual diagnosis faces enormous challenges. Thus, MRI-based artificial intelligence-assisted BM diagnosis is significant. Most of the existing deep learning (DL) methods for automatic BM detection try to ensure a good trade-off between precision and recall. However, due to the objective factors of the models, higher recall is often accompanied by higher number of false positive results. In real clinical auxiliary diagnosis, radiation oncologists are required to spend much effort to review these false positive results. In order to reduce false positive results while retaining high accuracy, a modified YOLOv5 algorithm is proposed in this paper. First, in order to focus on the important channels of the feature map, we add a convolutional block attention model to the neck structure. Furthermore, an additional prediction head is introduced for detecting small-size BMs. Finally, to distinguish between cerebral vessels and small-size BMs, a Swin transformer block is embedded into the smallest prediction head. With the introduction of the F2-score index to determine the most appropriate confidence threshold, the proposed method achieves a precision of 0.612 and recall of 0.904. Compared with existing methods, our proposed method shows superior performance with fewer false positive results. It is anticipated that the proposed method could reduce the workload of radiation oncologists in real clinical auxiliary diagnosis.

Analysis of Business Processes with Automatic Detection of KPI Thresholds and Process Discovery Based on Trace Variants

One effective way to analyze an event log of a complex business process is to filter the event log by a KPI threshold and then use an analysis algorithm. Event logs filtered by KPI thresholds are simpler and easier to understand than the original business process. KPI thresholds have conventionally had to be set through a trial-and-error process, but existing research has proposed an automatic KPI threshold detection method that reduces the time and effort required to search for a threshold value. In the existing method, an event log is first divided by an arbitrary number k, and a business process model is generated for the divided event log using a process discovery algorithm. By repeatedly aggregating similar business process models, it is possible to analyze how the business process models differ according to KPI values. However, the existing method requires trial-and-error to determine the value of k because the detection threshold and business process model vary depending on the value of k, which is time-consuming. Therefore, this paper proposes a method to automatically detect KPI thresholds by dividing event logs based on trace variants. Experimental results show that the business process models detected by the proposed method are simpler and the threshold detection time is significantly reduced.

Automatic measurement of the Cobb angle for adolescent idiopathic scoliosis using convolutional neural network

This study proposes a convolutional neural network method for automatic vertebrae detection and Cobb angle (CA) measurement on X-ray images for scoliosis. 1021 full-length X-ray images of the whole spine of patients with adolescent idiopathic scoliosis (AIS) were used for training and segmentation. The proposed AI algorithm's results were compared with those of the manual method by six doctors using the intraclass correlation coefficient (ICC). The ICCs recorded by six doctors and AI were excellent or good, with a value of 0.973 for the major curve in the standing position. The mean error between AI and doctors was not affected by the angle size, with AI tending to measure 1.7°–2.2° smaller than that measured by the doctors. The proposed method showed a high correlation with the doctors’ measurements, regardless of the CA size, doctors’ experience, and patient posture. The proposed method showed excellent reliability, indicating that it is a promising automated method for measuring CA in patients with AIS.

Frequency-Locked Loop Based New Automatic Phase-Shift Method for Active Islanding Detection of Three-Phase MicroGrid

This paper proposes an active Islanding Detection Method (IDM) integrating Frequency Locked-Loop (FLL) for the detection of voltage phase and frequency at the point of common coupling (PCC) and a modified Auto Phase Shift (APS) method for three-phase Distributed Energy Resource (DER) serving a local RLC load. The FLL is composed of a double second-order generalized integrator (DSOGI) to attenuate the harmonics and pass the fundamental positive sequence components in a frequency adaptive manner. Different from traditional APS methods, a new variable frequency term with an exponential factor is injected into the phase shift algorithm to reduce the region of Non-Detection Zone (NDZ). This modified approach enables the decentralized power generation system to detect the islanding phenomenon more quickly. Simulations and experimental tests conducted on a DG system on OPALRT (OP5600) and hardware test-bed demonstrate the behaviour of the proposed model within IEEE Standards. Additionally, a comparative evaluation was performed on the seamless transition of a microgrid (MG) from Grid-connected mode to Islanded mode and vice versa, using two different MGs, each having a single voltage source converter (VSC) and a local load but with control circuits incorporating DSOGI-FLL and ROGI-FLL respectively. Hardware testing results indicated that the control circuit based on ROGI-FLL demonstrated superior performance.

Enhancing Strawberry Harvesting Efficiency through Yolo-v7 Object Detection Assessment

Strawberry fruits which are rich in vitamin A and carotenoids offer benefits for maintaining healthy epithelial tissues and promoting maturity and growth. The intensive cultivation and swift maturation of strawberries make them susceptible to premature harvesting, leading to spoilage and financial losses for farmers. This underscores the need for an automated detection method to monitor strawberry development and accurately identify growth phases of fruits. To address this challenge, a dataset called Strawberry-DS, comprising 247 images captured in a greenhouse at the Agricultural Research Center in Giza, Egypt, is utilized in this research. The images of the dataset encompass various viewpoints, including top and angled perspectives, and illustrate six distinct growth phases: "green", “red”, "white", "turning", "early-turning" and "late-turning". This study employs the Yolo-v7 approach for object detection, enabling the recognition and classification of strawberries in different growth phases. The achieved mAP@.5 values for the growth phases are as follows: 0.37 for "green," 0.335 for "white," 0.505 for "early-turning," 1.0 for "turning," 0.337 for "late-turning," and 0.804 for "red". The comprehensive performance outcomes across all classes are as follows: precision at 0.792, recall at 0.575, mAP@.5 at 0.558, and mAP@.5:.95 at 0.46. Notably, these results show the efficacy of the proposed research, both in terms of performance evaluation and visual assessment, even when dealing with distracting scenarios involving imbalanced label distributions and unclear labeling of developmental phases of the fruits. This research article yields advantages such as achieving reasonable and reliable identification of strawberries, even when operating in real-time scenarios which also leads to a decrease in expenses associated with human labor.

The influence of EEG channels and features significance on automatic detection of epileptic waves in MECT

Modified Electric Convulsive Therapy (MECT) is an efficacious physical therapy in treating mental disorders. The occurrence of epilepsy is a crucial benchmark for evaluating therapeutic effectiveness. However, the medical field still lacks relevant research on automatically detecting epileptic waves in MECT. Therefore, this article proposes a novel automatic detection method of epileptic waves in MECT. In this article, EEG local features (time, frequency, and time-frequency domains) and global features (Pearson correlation coefficient) are combined for epileptic wave detection with SVM (Support Vector Machine). We researched the system with 15 EEG detection channels. The dataset under investigation contains EEG data from 22 patients who received MECT and presented with epileptic seizures. The results revealed that LA (Logarithm of Activity) feature exhibits the best classification significance. When epileptic waves appear, there is a decrease in the power ratio of delta waves and an increase in the power ratio of theta waves. Additionally, the complexity of EEG decreases while the correlation between EEG channels increases. The Cz, F4, and P3 channels exhibit the highest classification significance among all EEG channels. Furthermore, based on the channel classification significance, the EEG detection channels number can be reduced to 8. Similarly, based on the feature classification significance, the local feature number can be reduced from 9 to 3. These conclusions can improve detection efficiency and reduce the cost for MECT. Moreover, the method we proposed can effectively detect epileptic waves in MECT. This work can provide physicians with a reference for evaluating the effectiveness of MECT.

Fusion of udder temperature and size features for the automatic detection of dairy cow mastitis using deep learning

Mastitis seriously reduces the welfare and milk yield of dairy cows and affects the economic value of farms. Most dairy cow mastitis detection algorithms based on computer vision used the threshold classification method to detect mastitis only according to the temperature feature of cows’ udders, and the results were easily affected by the farm environment and individual cow characteristics. In this work, an automatic detection method for dairy cow mastitis using the fusion of udder temperature and size features based on deep learning was proposed. First, you only look once version 7 (YOLOv7) network was used to automatically detect the eye and udder regions of dairy cows, extract the corresponding temperatures, and construct an udder temperature feature vector. Then, the CenterNet network was used to automatically detect the keypoints of the udder region, calculate its corresponding size, and construct an udder size feature vector. Finally, both the temperature and size features of udders were fused, and the support vector machine (SVM) algorithm based on the wrapper was used to automatically detect the degree of mastitis. Thermal infrared videos of 196 dairy cows were used as the dataset for evaluating the performance of the proposed method, and the accuracy of the proposed method was 88.61%. The sensitivity and specificity values of the model for clinical mastitis (CM) were 87.50% and 94.03%, respectively, those for subclinical mastitis (SCM) were 81.25% and 91.94%, respectively. The proposed method constitutes a promising approach for automatic diagnosis in the early stages of dairy cow mastitis, and it can be used for objective monitoring and optimal management of commercial farms.

Automatic Detection and Recognition Method of Chinese Clay Tiles Based on YOLOv4: A Case Study in Macau

ABSTRACT With the rapid growth of global urbanization and the rising demand for sustainable development, it is essential to study the performance and durability of building materials. As a traditional and widely employed building material, Chinese clay tiles play a significant role in traditional Chinese architecture. However, traditional methods for assessing structural surface damage necessitate the time-consuming and labor-intensive assessment and judgment of trained professionals. Consequently, it is crucial to employ machine learning techniques for automatic damage type identification. This study identifies the types of damage to Chinese clay tiles in Macau by employing machine learning techniques and the YOLOv4 object detection model. A total of 363 photographs of on-site Chinese clay tiles were used as training samples, and 200 epochs of the model training were performed. The primary findings of this study are as follows: (1) The machine learning method, based on the YOLOv4 model, provides an effective and precise solution for the automatic identification of Chinese clay tiles damage types, overcoming the human and time-cost constraints of conventional evaluation methods. (2) The detection accuracy of the detection model in this study is 95.42% for the detection of Chinese clay tiles cracks, 80.91% for the detection of stains, and 89.34% for the detection of surface wear, with an overall accuracy of 88.98%, which meets the basic detection requirements. (3) The experimental results demonstrate the viability and efficacy of the proposed method for identifying clay tile damage types and provide a method reference for the preservation and sustainable development of historical buildings.

A decision tree model of hypertension among college students in Yunnan Province, China

Purpose Previous studies have indicated that the prevalence rate of hypertension in adolescents is high, but it has not received much attention and the influencing factors are unclear, especially in Yunnan Province, China. Materials and methods A cluster sampling method was used to investigate 4781 freshmen in a college in Kunming, Yunnan Province from November to December. Demographic and lifestyle data were collected using questionnaires, and height, weight and blood pressure were measured. Decision tree model of hypertension in college students was established by Chi-square automatic interactive detection method. Results Prevalence of prehypertension of systolic blood pressure (SBP) and diastolic blood pressure (DBP) were detected in 33.9% and 32.1%, respectively. Prevalence of hypertension of SBP and DBP was detected in 1.2% and 7.2%, respectively. The hypertension and prehypertension decision tree of SBP has gender (χ 2 = 728.64, p < .001) at the first level and body mass index (BMI) (boys: χ 2 = 55.98, p < .001; girls: χ 2 = 79.58, p < .001) at the second level. The hypertension and prehypertension decision tree of DBP has gender (χ 2 = 381.83, p < .001) at the first level, BMI (boys: χ 2 = 40.54, p < .001; girls: χ 2 = 48.79, p < .001) at the second level, only children (χ 2 = 6.43, p = .04) and red wine consumption (χ 2 = 8.17, p = .017) at the third level. Conclusions The present study suggests that gender, BMI, only children and red wine consumption were the main factors affecting hypertension in college students in southwest border areas of China.

MANet: Multi-branch attention auxiliary learning for lung nodule detection and segmentation

Background and objective: Pulmonary nodule detection and segmentation are currently two primary tasks in analyzing chest computed tomography (Chest CT) in order to detect signs of lung cancer, thereby providing early treatment measures to reduce mortality. Even though there are many proposed methods to reduce false positives for obtaining effective detection results, distinguishing between the pulmonary nodule and background region remains challenging because their biological characteristics are similar and varied in size. The purpose of our work is to propose a method for automatic nodule detection and segmentation in Chest CT by enhancing the feature information of pulmonary nodules.Methods: We propose a new UNet-based backbone with multi-branch attention auxiliary learning mechanism, which contains three novel modules, namely, Projection module, Fast Cascading Context module, and Boundary Enhancement module, to further enhance the nodule feature representation. Based on that, we build MANet, a lung nodule localization network that simultaneously detects and segments precise nodule positions. Furthermore, our MANet contains a Proposal Refinement step which refines initially generated proposals to effectively reduce false positives and thereby produce the segmentation quality.Results: Comprehensive experiments on the combination of two benchmarks LUNA16 and LIDC-IDRI show that our proposed model outperforms state-of-the-art methods in the tasks of nodule detection and segmentation tasks in terms of FROC, IoU, and DSC metrics. Our method reports an average FROC score of 88.11% in lung nodule detection. For the lung nodule segmentation, the results reach an average IoU score of 71.29% and a DSC score of 82.74%. The ablation study also shows the effectiveness of the new modules which can be integrated into other UNet-based models.Conclusions: The experiments demonstrated our method with multi-branch attention auxiliary learning ability are a promising approach for detecting and segmenting the pulmonary nodule instances compared to the original UNet design.

Context and scale-aware YOLO for welding defect detection

Radiography testing for welding defect detection is an essential inspection procedure to ensure welding quality. However, detecting these defects is a challenging task because they have various size and aspect ratio characteristics and low perceptiveness due to the low luminance and contrast characteristics of the radiography image (RI). To address these difficulties, this paper proposes a twin model-based automatic welding defect detection method to reveal welding defects of various sizes and aspect ratios more accurately. In addition, we propose a new image adjustment technique that is optimized to improve the accuracy of welding defect detection by adaptively adjusting the luminance and contrast of a given RI. The proposed method consists of three steps: preprocessing for defect detection (PDD), context-aware image adjustment (CIA), and scale-aware defect detection (SDD). In the PDD step, we extract the region of interest from a RI based on text detection by removing regions unnecessary for welding defect detection. In the CIA step, we adaptively optimize a given image to improve the detection accuracy by utilizing a differentiable parametric module that performs image enhancement filtering. In the SDD step, we define a twin model that outputs the embeddings of different scales from the adjusted RI to detect the defects with various scales accurately. At the inference stage of the detection model, we ensemble the results using a weighted fusion of the detection results from the twin model to take advantage of the ensemble strategy. The experimental results indicate that the proposed method achieves outstanding detection accuracy compared to the benchmark methods.

A Method for Obtaining 3D Point Cloud Data by Combining 2D Image Segmentation and Depth Information of Pigs.

This paper proposes a method for automatic pig detection and segmentation using RGB-D data for precision livestock farming. The proposed method combines the enhanced YOLOv5s model with the Res2Net bottleneck structure, resulting in improved fine-grained feature extraction and ultimately enhancing the precision of pig detection and segmentation in 2D images. Additionally, the method facilitates the acquisition of 3D point cloud data of pigs in a simpler and more efficient way by using the pig mask obtained in 2D detection and segmentation and combining it with depth information. To evaluate the effectiveness of the proposed method, two datasets were constructed. The first dataset consists of 5400 images captured in various pig pens under diverse lighting conditions, while the second dataset was obtained from the UK. The experimental results demonstrated that the improved YOLOv5s_Res2Net achieved a mAP@0.5:0.95 of 89.6% and 84.8% for both pig detection and segmentation tasks on our dataset, while achieving a mAP@0.5:0.95 of 93.4% and 89.4% on the Edinburgh pig behaviour dataset. This approach provides valuable insights for improving pig management, conducting welfare assessments, and estimating weight accurately.

SE-YOLOv7 Landslide Detection Algorithm Based on Attention Mechanism and Improved Loss Function

With the continuous development of computer vision technology, more and more landslide identification detection tasks have started to shift from manual visual interpretation to automatic computer identification, and automatic landslide detection methods based on remote sensing satellite images and deep learning have been gradually developed. However, most existing algorithms often have the problem of low precision and weak generalization in landslide detection. Based on the Google Earth Engine platform, this study selected landslide image data from 24 study areas in China and established the DN landslide sample dataset, which contains a total of 1440 landslide samples. The original YOLOv7 algorithm model was improved and optimized by applying the SE squeezed attention mechanism and VariFocal loss function to construct the SE-YOLOv7 model to realize the automatic detection of landslides in remote sensing images. The experimental results show that the mAP, Precision value, Recall value, and F1-Score of the improved SE-YOLOv7 model for landslide identification are 91.15%, 93.35%, 94.54%, and 93.94%, respectively. At the same time, through a field investigation and verification study in Qianyang County, Baoji City, Shaanxi Province, comparing the detection results of SE-YOLOv7, it is concluded that the improved SE-YOLOv7 can locate the landslide location more accurately, detect the landslide range more accurately, and have fewer missed detections. The research results show that the algorithm model has strong detection accuracy for many types of landslide image data, which provides a technical reference for future research on landslide detection based on remote sensing images.

Warm-core eddy effects on sound propagation in the South China sea

The spatial and temporal redistribution of sound energy caused by a warm eddy was measured via a multiday experiment conducted in the South China Sea, utilizing two vertical line arrays, a mooring source, and some wide-band explosive sources. In the experiment area, a warm eddy was identified and tracked using an automatic detection method combined with the empirically reconstructed data. During the experimental period, the warm eddy diminished in size and kinetic energy until it vanished. The influence of the warm eddy on sound propagation during its lifespan is comprehensively analyzed and explained. The experimental acoustic results and simulations based on dynamic hydrographic data demonstrate that energy is redistributed both spatially and temporally due to the presence of the warm eddy. In comparison to the environment without an eddy, the first convergence zone disappears and the high-energy region appears in the typical position of the first shadow zone. The oscillating disturbance in energy is mainly affected by the fluctuation of sound speed caused by the warm eddy.

An automatic cephalometric landmark detection method based on heatmap regression and Monte Carlo dropout.

Cephalometric analysis plays an important role in orthodontic diagnosis and treatment planning. It depends on the detection of multiple landmarks, while the process is time-consuming and tedious. Although some deep learning-based automatic landmark detection algorithms have achieved excellent performance, most of them adopt multi-stage models increasing the complexity and detection time. Meanwhile, few studies focused on the uncertainty of detection results, thereby ignoring its significant clinical value. In this paper, we propose a novel approach based on heatmap regression for landmark detection, which can achieve competitive accuracy and good robustness with only one step. Furthermore, by applying Monte Carlo dropout to a U-shaped convolutional neural network, we can obtain not only the coordinate of each landmark but also the corresponding simple uncertainty, so that doctors can pay more attention to those landmarks with higher uncertainty. The evaluation results showed the mean radial error is 1.39±1.06mm and the average successful detection rate is 79.65%, 97.22% within 2mm, 4mm for the IEEE ISBI2015 Test Dataset 1, the indicators for the IEEE ISBI2015 Test Dataset 2 are 1.33±0.93mm, 80.05% and 97.53%, respectively. Our method has the potential to become an assistant tool in clinical practice. Automatic and accurate detection with uncertainty analysis is expected to help guide the doctor's judgment.

A Multi-Feature Fusion-Based Automatic Detection Method for High-Severity Defects

It is crucial to detect high-severity defects, such as memory leaks that can result in system crashes or severe resource depletion, in order to reduce software development costs and ensure software quality and reliability. The primary cause of high-severity defects is usually resource scheduling errors, and in the program source code, these defects have contextual features that require defect context to confirm their existence. In the context of utilizing machine learning methods for defect automatic confirmation, the single-feature label method cannot achieve high-precision defect confirmation results for high-severity defects. Therefore, a multi-feature fusion defect automatic confirmation method is proposed. The label generation method solves the dimensionality disaster problem caused by multi-feature fusion by fusing features with strong correlations, improving the classifier’s performance. This method extracts node features and basic path features from the program dependency graph and designs high-severity contextual defect confirmation labels combined with contextual features. Finally, an optimized Support Vector Machine is used to train the automatic detection model for high-severity defects. This study uses open-source programs to manually implant defects for high-severity defect confirmation verification. The experimental results show that compared with existing methods, this model significantly improves the efficiency of confirming high-severity defects.