Performance Of Detection Algorithm Research Articles

Shallow mud detection algorithm for submarine channels based on improved YOLOv5s

Submarine mud poses a risk to channel navigation safety. Traditional detection methods lack efficiency and accuracy. As a result, this paper proposed an enhanced shallow submarine mud detection algorithm, leveraging an improved YOLOv5s model to increase accuracy and effectiveness in identifying such hazards in marine channels. Firstly, the sub-bottom profiler was employed to assess the submarine channel of Lianyungang Port to acquire the image data of the shallow mud sound print. Concurrently, the analysis incorporated the characteristics of changes in sound intensity peaks to precisely identify the shallow mud's location. Furthermore, the incorporation of C2F feature module into the backbone module enhances the gradient flow of the algorithm, augments the feature extraction information, and improves the algorithm's detection performance. Subsequently, Efficient Multi-Scale Attention (EMA) mechanism is incorporated into the neck module, aiming to optimize the algorithm's channel dimensions, minimize computational overhead, and enhance its detection efficiency. Finally, the study introduced Normalized Wasserstein Distance (NWD) loss function into bounding box regression loss function. This integration effectively addresses the issue of multi-scale defects, emphasizes the transformation of target planar position deviation, and improves the accuracy of the algorithm's detection capabilities. The results indicate that the improved YOLOv5s-EF algorithm outperforms the original YOLOv5s algorithm and other widely used detection algorithms. It achieved a validation set precision rate of 97.8%, recall rate of 97.6%, F1 value of 97.7%, mean Average Precision (mAP)@0.5 of 98.2%, mAP@0.95 of 69.6%, and Frames Per Second (FPS) of 51.8. YOLOv5s-EF algorithm proposed in this study offers a novel technical approach for detecting mud in submarine channels, which is importance for ensuring the safe operation and maintenance of dredging in such channels.

The Three Hundred: Contrasting cluster galaxy density in hydrodynamical and dark matter simulations

Cluster number counts at visible and IR wavelengths will be a key cosmological probe in the next decade thanks to the Euclid satellite mission. For this purpose, the performance of cluster detection algorithms, which at these wavelengths are sensitive to the spatial distributions of the cluster galaxy members and their luminosity functions, need to be accurately characterized. Using hydrodynamical and dark-matter-only simulations, we studied a complete sample of massive clusters beyond 7 (5) times 1014 odot $ at redshift 0 (1) on a $(1.48 \ Gpc )^3$ volume. We find that the mass resolution of the current hydrodynamical simulations (1.5 times 10$^9$ M$_ odot $) is not enough to characterize the luminosity function of the sample in the perspective of Euclid data. Nevertheless, these simulations are still useful to characterize the spatial distribution of the cluster substructures assuming a common relative mass threshold for the different flavours and resolutions. By comparing with the dark-matter-only version of these simulations, we demonstrate that baryonic physics preserves significantly low-mass subhalos (galaxies), as has also been observed in previous studies with less statistics. Furthermore, by comparing the hydro simulations with higher resolution dark-matter-only simulations of the same objects and taking the same limit in subhalo mass, we find galaxy density profiles that are significantly more cuspy towards the centre of the clusters, where the low-mass substructures tend to concentrate. We conclude that using a dark-matter-only simulation may lead to some biases on the spatial distribution and density of galaxy cluster members. Based on the preliminary analysis of few high-resolution hydro simulations we conclude that a mass resolution of 1.8 times 10$^8$ h$^ $ M$_ odot $ will be needed for simulations to approach the expected magnitude limits for the Euclid survey. These simulations are currently under way.

Opportunistic Identification of Vertebral Compression Fractures on CT Scans of the Chest and Abdomen, Using an AI Algorithm, in a Real-Life Setting.

This study evaluated the performance of a vertebral fracture detection algorithm (HealthVCF) in a real-life setting and assessed the impact on treatment and diagnostic workflow. HealthVCF was used to identify moderate and severe vertebral compression fractures (VCF) at a Danish hospital. Around 10,000 CT scans were processed by the HealthVCF and CT scans positive for VCF formed both the baseline and 6-months follow-up cohort. To determine performance of the algorithm 1000 CT scans were evaluated by specialized radiographers to determine performance of the algorithm. Sensitivity was 0.68 (CI 0.581-0.776) and specificity 0.91 (CI 0.89-0.928). At 6-months follow-up, 18% of the 538 patients in the retrospective cohort were dead, 78 patients had been referred for a DXA scan, while 25 patients had been diagnosed with osteoporosis. A higher mortality rate was seen in patients not known with osteoporosis at baseline compared to patients known with osteoporosis at baseline, 12.8% versus 22.6% (p = 0.003). Patients receiving bisphosphonates had a lower mortality rate (9.6%) compared to the rest of the population (20.9%) (p = 0.003). HealthVCF demonstrated a poorer performance than expected, and the tested version is not generalizable to the Danish population. Based on its specificity, the HealthVCF can be used as a tool to prioritize resources in opportunistic identification of VCF's. Implementing such a tool on its own only resulted in a small number of new diagnoses of osteoporosis and referrals to DXA scans during a 6-month follow-up period. To increase efficiency, the HealthVCF should be integrated with Fracture Liaison Services (FLS).

PODB: A learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions

Due to its insensitivity to light intensity and the capability to capture multidimensional information, polarimetric imaging technology has been proven to have advantages over traditional intensity-based imaging techniques for object detection tasks in adverse environmental conditions, particularly in road traffic scenarios. Recently, with the rapid development of artificial intelligence technology, deep learning (DL)-powered object detection techniques can further enhance recognition accuracy and algorithm robustness. This improvement is made possible by the ability of DL technology to leverage large datasets and extract deeper levels of target-specific features. However, constructing large-scale polarimetric datasets poses challenges as obtaining polarimetric information requires multiple captures of intensity images. In other words, the workload is several times higher compared to traditional imaging techniques. To address the current scarcity of polarimetric datasets and evaluate the practical performance of various algorithms on polarimetric datasets, this paper proposes a Polarimetric Object Detection Benchmark (PODB) dataset. The PODB provides an integrated quality evaluation framework for DL-based object detection algorithms in complex road scenes by incorporating polarimetric imaging. Besides, we conducted extensive object detection experiments using the PODB, which allowed for a comprehensive validation and performance evaluation of effective benchmark algorithms. Furthermore, a physics-based multi-scale image fusion cascaded object detection neural network model is proposed. By combining the multidimensional information provided by polarized images with an adaptive learning multi-decision object detection neural network model, the recognition accuracy of complex road scenes in adverse weather conditions has been improved by approximately 10%. Additionally, we anticipate that PODB will serve as an effective platform for evaluating and comparing the performance of object detection algorithms, as well as providing researchers with a baseline for future studies in developing new DL-based methods.

PiDiNet-TIR: An improved edge detection algorithm for weakly textured thermal infrared images based on PiDiNet

In order to solve the problems such as difficulties in extracting image edge information caused by low contrast and blurred edges of thermal infrared images, a thermal infrared image edge detection algorithm PiDiNet-TIR constructed based on the PiDiNet model is proposed. On the basis of the visible light image dataset BSDS500, the visible light image is grayed out, noise is added, and contrast is reduced to construct the thermal infrared image edge dataset I R-BSDS500, which provides image data for model training and testing. Deeply study the theory of PiDiNet model, add rich convolution mechanism to its backbone network, improve the activation function, pooling layer and up-sampling module, study the SimAM attention mechanism and add it to the side network. Using the open-source thermal infrared image dataset and homemade thermal infrared images for testing, we compare and analyze the mean square error (MSE), structural similarity of image (SSIM), feature similarity of image (FSIM), and Frames Per Second (FPS)of different detection algorithms, such as HED, RCF, DexiNet, PiDiNet, and the algorithm proposed in this paper. The results of image evaluation parameters prove that the edge detection algorithm proposed in this paper has high feature extraction efficiency and feature expression ability, and the algorithm detection performance is higher than other algorithms.

Evaluation of an algorithm-guided photoplethysmography for atrial fibrillation burden using a smartwatch.

Wearable devices based on the PPG algorithm can detect atrial fibrillation (AF) effectively. However, further investigation of its application on long-term, continuous monitoring of AF burden is warranted. The performance of a smartwatch with continuous photoplethysmography (PPG) and PPG-based algorithms for AF burden estimation was evaluated in a prospective study enrolling AF patients admitted to Beijing Anzhen Hospital for catheter ablation from September to November 2022. A continuous Electrocardiograph patch (ECG) was used as the reference device to validate algorithm performance for AF detection in 30-s intervals. A total of 578669 non-overlapping 30-s intervals for PPG and ECG each from 245 eligible patients were generated. An interval-level sensitivity of PPG was 96.3% (95% CI 96.2%-96.4%), and specificity was 99.5% (95% CI 99.5%-99.6%) for the estimation of AF burden. AF burden estimation by PPG was highly correlated with AF burden calculated by ECG via Pearson correlation coefficient (R2 = 0.996) with a mean difference of -0.59 (95% limits of agreement, -7.9% to 6.7%). The subgroup study showed the robust performance of the algorithm in different subgroups, including heart rate and different hours of the day. Our results showed the smartwatch with an algorithm-based PPG monitor has good accuracy and stability in continuously monitoring AF burden compared with ECG patch monitors, indicating its potential for diagnosing and managing AF.

MACHINE WHELL EDGE DETECTION MORPHOLOGICAL OPERATIONS

One of the critical issues of image processing, defined as obtaining useful information from the image and improving the quality of the image, is edge detection. How edge detection performance will be affected by adding morphological operators to edge detection algorithms is among the issues that have not been fully resolved. In the study, Canny and Sobel edge detection algorithms were applied to different milling cutters used in machinability. Morphological operators were applied to the determined edges, and their effects on the edges were examined. Mean Square Error (MSE) and Peak Signal Noise Ratio (PSNR) values were used to compare the performances of edge detection algorithms. According to MSE and PSNR results, it was seen that the Canny algorithm gave better results than the Sobel algorithm. In addition, it was concluded that the images obtained as a result of the applied morphological operations provided better performance than the images that were not applied for both Canny and Sobel algorithms.

Are better AI algorithms for breast cancer detection also better at predicting risk? A paired case–control study

BackgroundThere is increasing evidence that artificial intelligence (AI) breast cancer risk evaluation tools using digital mammograms are highly informative for 1–6 years following a negative screening examination. We hypothesized that algorithms that have previously been shown to work well for cancer detection will also work well for risk assessment and that performance of algorithms for detection and risk assessment is correlated.MethodsTo evaluate our hypothesis, we designed a case-control study using paired mammograms at diagnosis and at the previous screening visit. The study included n = 3386 women from the OPTIMAM registry, that includes mammograms from women diagnosed with breast cancer in the English breast screening program 2010–2019. Cases were diagnosed with invasive breast cancer or ductal carcinoma in situ at screening and were selected if they had a mammogram available at the screening examination that led to detection, and a paired mammogram at their previous screening visit 3y prior to detection when no cancer was detected. Controls without cancer were matched 1:1 to cases based on age (year), screening site, and mammography machine type. Risk assessment was conducted using a deep-learning model designed for breast cancer risk assessment (Mirai), and three open-source deep-learning algorithms designed for breast cancer detection. Discrimination was assessed using a matched area under the curve (AUC) statistic.ResultsOverall performance using the paired mammograms followed the same order by algorithm for risk assessment (AUC range 0.59–0.67) and detection (AUC 0.81–0.89), with Mirai performing best for both. There was also a correlation in performance for risk and detection within algorithms by cancer size, with much greater accuracy for large cancers (30 mm+, detection AUC: 0.88–0.92; risk AUC: 0.64–0.74) than smaller cancers (0 to < 10 mm, detection AUC: 0.73–0.86, risk AUC: 0.54–0.64). Mirai was relatively strong for risk assessment of smaller cancers (0 to < 10 mm, risk, Mirai AUC: 0.64 (95% CI 0.57 to 0.70); other algorithms AUC 0.54–0.56).ConclusionsImprovements in risk assessment could stem from enhancing cancer detection capabilities of smaller cancers. Other state-of-the-art AI detection algorithms with high performance for smaller cancers might achieve relatively high performance for risk assessment.

Improving the detection of sleep slow oscillations in electroencephalographic data.

We aimed to build a tool which facilitates manual labeling of sleep slow oscillations (SOs) and evaluate the performance of traditional sleep SO detection algorithms on such a manually labeled data set. We sought to develop improved methods for SO detection. SOs in polysomnographic recordings acquired during nap time from ten older adults were manually labeled using a custom built graphical user interface tool. Three automatic SO detection algorithms previously used in the literature were evaluated on this data set. Additional machine learning and deep learning algorithms were trained on the manually labeled data set. Our custom built tool significantly decreased the time needed for manual labeling, allowing us to manually inspect 96,277 potential SO events. The three automatic SO detection algorithms showed relatively low accuracy (max. 61.08%), but results were qualitatively similar, with SO density and amplitude increasing with sleep depth. The machine learning and deep learning algorithms showed higher accuracy (best: 99.20%) while maintaining a low prediction time. Accurate detection of SO events is important for investigating their role in memory consolidation. In this context, our tool and proposed methods can provide significant help in identifying these events.

Improving lesion detection in mammograms by leveraging a Cycle-GAN-based lesion remover

BackgroundThe wide heterogeneity in the appearance of breast lesions and normal breast structures can confuse computerized detection algorithms. Our purpose was therefore to develop a Lesion Highlighter (LH) that can improve the performance of computer-aided detection algorithms for detecting breast cancer on screening mammograms.MethodsWe hypothesized that a Cycle-GAN based Lesion Remover (LR) could act as an LH, which can improve the performance of lesion detection algorithms. We used 10,310 screening mammograms from 4,832 women that included 4,942 recalled lesions (BI-RADS 0) and 5,368 normal results (BI-RADS 1). We divided the dataset into Train:Validate:Test folds with the ratios of 0.64:0.16:0.2. We segmented image patches (400 × 400 pixels) from either lesions marked by MQSA radiologists or normal tissue in mammograms. We trained a Cycle-GAN to develop two GANs, where each GAN transferred the style of one image to another. We refer to the GAN transferring the style of a lesion to normal breast tissue as the LR. We then highlighted the lesion by color-fusing the mammogram after applying the LR to its original. Using ResNet18, DenseNet201, EfficientNetV2, and Vision Transformer as backbone architectures, we trained three deep networks for each architecture, one trained on lesion highlighted mammograms (Highlighted), another trained on the original mammograms (Baseline), and Highlighted and Baseline combined (Combined). We conducted ROC analysis for the three versions of each deep network on the test set.ResultsThe Combined version of all networks achieved AUCs ranging from 0.963 to 0.974 for identifying the image with a recalled lesion from a normal breast tissue image, which was statistically improved (p-value < 0.001) over their Baseline versions with AUCs that ranged from 0.914 to 0.967.ConclusionsOur results showed that a Cycle-GAN based LR is effective for enhancing lesion conspicuity and this can improve the performance of a detection algorithm.

Nodule detection and generation on chest X-rays: NODE21 Challenge.

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task. To address this, we organized a public research challenge, NODE21, aimed at the detection and generation of lung nodules in chest X-rays. While the detection track assesses state-of-the-art nodule detection systems, the generation track determines the utility of nodule generation algorithms to augment training data and hence improve the performance of the detection systems. This paper summarizes the results of the NODE21 challenge and performs extensive additional experiments to examine the impact of the synthetically generated nodule training images on the detection algorithm performance.

On the performance of pothole detection algorithms enhanced via data augmentation

Road infrastructure is necessary for any country to function as daily life depends upon it. Transport authorities monitor road infrastructure to identify distressed areas and repair them, enhancing users’ comfort and safety. Major steps have been taken in automating road monitoring using sensing- and vision-based technologies, reducing the level of subjectivity caused by traditional manual inspection processes. However, automated detection of distressed areas is often challenged by an insufficient amount of training data or uneven class balance within datasets. Data augmentation techniques offer the opportunity to enlarge the size and quality of existing datasets. This paper investigates how various augmentation techniques impact the performance of a set of representative detection algorithms applied to detecting highway potholes. The results suggest that: firstly, no specific augmentation seems to be more beneficial than the others in this domain; and second, using a moderate amount of augmentation techniques can provide performance gains. This work forms the basis for performance improvement of multiple detection algorithms, used for transport infrastructure management, and it consequently contributes to enhanced transport systems simulation and monitoring.

Analysing the performance of Viola-Jones and multi-task convolution neural networks face detection algorithms using real-time video sequences

Analysing the performance of Viola-Jones and multi-task convolution neural networks face detection algorithms using real-time video sequences

Evaluating a Periapical Lesion Detection CNN on a Clinically Representative CBCT Dataset-A Validation Study.

The aim of this validation study was to comprehensively evaluate the performance and generalization capability of a deep learning-based periapical lesion detection algorithm on a clinically representative cone-beam computed tomography (CBCT) dataset and test for non-inferiority. The evaluation involved 195 CBCT images of adult upper and lower jaws, where sensitivity and specificity metrics were calculated for all teeth, stratified by jaw, and stratified by tooth type. Furthermore, each lesion was assigned a periapical index score based on its size to enable a score-based evaluation. Non-inferiority tests were conducted with proportions of 90% for sensitivity and 82% for specificity. The algorithm achieved an overall sensitivity of 86.7% and a specificity of 84.3%. The non-inferiority test indicated the rejection of the null hypothesis for specificity but not for sensitivity. However, when excluding lesions with a periapical index score of one (i.e., very small lesions), the sensitivity improved to 90.4%. Despite the challenges posed by the dataset, the algorithm demonstrated promising results. Nevertheless, further improvements are needed to enhance the algorithm's robustness, particularly in detecting very small lesions and the handling of artifacts and outliers commonly encountered in real-world clinical scenarios.

An intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network

Intrusion Detection System (IDS) can ensure the network security by identifying network intrusions according to the abnormal traffic data. However, the intrusion detection data has the problem of high dimensionality and changes with network and attack environments, which leads to the poor performance and poor portability of intrusion detection algorithms. Therefore, this paper proposes an intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network. Firstly, a feature selection method based on symmetric uncertainty and approximate Markov blanket is proposed, which fully considers the correlation and redundancy of features, and also the correlation between combined features and the class label, so as to reduce the data dimensionality. Secondly, the CNN-LSTM classifier fused with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is used to extract the spatial features and temporal features to improve the classification performance. Finally, the Particle Swarm Optimization (PSO) algorithm is improved and used to automatically optimize the hyperparameters of the classifier, so that the classifier can be applied to different intrusion detection datasets with better generalization ability and portability. Experiments have verified the effectiveness and superiority of the proposed algorithm on multiple evaluation indicators.

Data-Quality Assessment for Digital Twins Targeting Multi-Component Degradation in Industrial Internet of Things (IIoT)-Enabled Smart Infrastructure Systems

In the development of analytics for PHM applications, a lot of emphasis has been placed on data transformation for optimal model development without enough consideration for the repeatability of the measurement systems producing the data. This paper explores the relationship between data quality, defined as the measurement system analysis (MSA) process, and the performance of fault detection and isolation (FDI) algorithms within smart infrastructure systems. This research employs a comprehensive methodology, starting with an MSA process for data-quality evaluation and leading to the development and evaluation of fault detection and isolation (FDI) algorithms. During the MSA phase, the repeatability of a water distribution system’s measurement system is examined to characterise variations within the system. A data-quality process is defined to gauge data quality. Synthetic data are introduced with varying data-quality levels to investigate their impact on FDI algorithm development. Key findings reveal the complex relationship between data quality and FDI algorithm performance. Synthetic data, even with lower quality, can improve the performance of statistical process control (SPC) models, whereas data-driven approaches benefit from high-quality datasets. The study underscores the importance of customising FDI algorithms based on data quality. A framework for instantiating the MSA process for IIoT applications is also suggested. By bridging data-quality assessment with data-driven FDI, this research contributes to the design of digital twins for IIoT-enabled smart infrastructure systems. Further research on the practical implementation of the MSA process for edge analytics for PHM applications will be considered as part of our future research.

Research on Forest Flame Detection Algorithm Based on a Lightweight Neural Network

To solve the problem of the poor performance of a flame detection algorithm in a complex forest background, such as poor detection performance, insensitivity to small targets, and excessive computational load, there is an urgent need for a lightweight, high-accuracy, real-time detection system. This paper introduces a lightweight object-detection algorithm called GS-YOLOv5s, which is based on the YOLOv5s baseline model and incorporates a multi-scale feature fusion knowledge distillation architecture. Firstly, the ghost shuffle convolution bottleneck is applied to obtain richer gradient information through branching. Secondly, the WIoU loss function is used to address the issues of GIoU related to model optimization, slow convergence, and inaccurate regression. Finally, a knowledge distillation algorithm based on feature fusion is employed to further improve its accuracy. Experimental results based on the dataset show that compared to the YOLOv5s baseline model, the proposed algorithm reduces the number of parameters and floating-point operations by approximately 26% and 36%, respectively. Moreover, it achieved a 3.1% improvement in mAP0.5 compared to YOLOv5s. The experiments demonstrate that GS-YOLOv5s, based on multi-scale feature fusion, not only enhances detection accuracy but also meets the requirements of lightweight and real-time detection in forest fire detection, commendably improving the practicality of flame-detection algorithms.

A Study of Two Periodogram Algorithms for Improving the Detection of Small Transiting Planets

The sensitivities of two periodograms are compared for weak signal planet detection in transit surveys: the widely used Box Least Squares (BLS) algorithm following light curve detrending and the Transit Comb Filter (TCF) algorithm following autoregressive ARIMA modeling. Small depth transits are injected into light curves with different simulated noise characteristics. Two measures of spectral peak significance are examined: the periodogram signal-to-noise ratio (S/N) and a false alarm probability (FAP) based on the generalized extreme value distribution. The relative performance of the BLS and TCF algorithms for small planet detection is examined for a range of light curve characteristics, including orbital period, transit duration, depth, number of transits, and type of noise. We find that the TCF periodogram applied to ARIMA fit residuals with the S/N detection metric is preferred when short-memory autocorrelation is present in the detrended light curve and even when the light curve noise had white Gaussian noise. BLS is more sensitive to small planets only under limited circumstances with the FAP metric. BLS periodogram characteristics are inferior when autocorrelated noise is present due to heteroscedastic noise and false period detection. Application of these methods to TESS light curves with known small exoplanets confirms our simulation results. The study ends with a decision tree that advises transit survey scientists on procedures to detect small planets most efficiently. The use of ARIMA detrending and TCF periodograms can significantly improve the sensitivity of any transit survey with regularly spaced cadence.

An acceleration and optimization method of edge computing using filter level pruning

In order to reduce the complexity of the network and the amount of floating-point computation, this paper proposes an efficient target detection algorithm. Firstly, we use the feature of deep separable convolution to reduce the amount of calculation and design a target detection network structure. Based on the new network structure, the filter is pruned by using the size of the L1 norm value as the threshold to further compress the network model. Then it is deployed on the embedded GPU platform of the edge device for verification, and excellent algorithm performance is achieved. The combination of deep separable convolution and filter-level pruning greatly improves the computational performance of the target detection algorithm on the edge device.

Synthetic Data Generation Based on RDB-CycleGAN for Industrial Object Detection

Deep learning-based methods have demonstrated remarkable success in object detection tasks when abundant training data are available. However, in the industrial domain, acquiring a sufficient amount of training data has been a challenge. Currently, many synthetic datasets are created using 3D modeling software, which can simulate real-world scenarios and objects but often cannot achieve complete accuracy and realism. In this paper, we propose a synthetic data generation framework for industrial object detection tasks based on image-to-image translation. To address the issue of low image quality that can arise during the image translation process, we have replaced the original feature extraction module with the Residual Dense Block (RDB) module. We employ the RDB-CycleGAN network to transform CAD models into realistic images. Additionally, we have introduced the SSIM loss function to strengthen the network constraints of the generator and conducted a quantitative analysis of the improved RDB-CycleGAN-generated synthetic data. To evaluate the effectiveness of our proposed method, the synthetic data we generate effectively enhance the performance of object detection algorithms on real images. Compared to using CAD models directly, synthetic data adapt better to real-world scenarios and improve the model’s generalization ability.