Correct Detection Rate Research Articles

A novel AE source localization method using clustering detection to eliminate abnormal arrivals

Due to the significant effect of abnormal arrivals on localization accuracy, a novel acoustic emission (AE) source localization method using clustering detection to eliminate abnormal arrivals is proposed in the paper. Firstly, iterative weight estimation is utilized to obtain accurate equation residuals. Secondly, according to the distribution of equation residuals, clustering detection is used to identify and exclude abnormal arrivals. Thirdly, the AE source coordinate is recalculated with remaining normal arrivals. Experimental results of pencil-lead breaks indicate that the proposed method can achieve a better localization result with and without abnormal arrivals. The results of simulation tests further demonstrate that the proposed method possesses higher localization accuracy and robustness under different anomaly ratios and scales; even with abnormal arrivals as high as 30%, the proposed localization method still holds a correct detection rate of 91.85%.

Improving power theft detection using efficient clustering and ensemble classification

One of the main concerns of power generation systems around the world is power theft. This research proposes a framework that merges clustering and classification together in order to power theft detection. Due to the fact that most datasets do not have abnormal samples or are few, we have added abnormal samples to the original datasets using artificial attacks to create balance in the datasets and increase the correct detection rate. We improved the crow search algorithm (CSA) and used the weight feature of Crows to improve performance of clustering phase. Also, to create balance between diversification and intensification, we calculated the awareness probability parameter (AP) dynamically at iterations of the algorithm. To evaluate the performance, we used the cross validation technique have used the stacking technique in its training phase. The results of extensive experiments on three reference datasets showed high performance to detect power theft. The evaluation results showed that if the data is collected correctly and sufficiently, this framework can effectively detect power theft in any actual power grid. Also, for new attacks, if their patterns can be detected from the data, it is easily possible to implement these types of attacks.

A neural network-based approach for the detection of heavy precipitation using GNSS observations and surface meteorological data

Recent years have witnessed a growing interest in using GNSS observations to detect heavy precipitation. In this study, a neural network-based (NN-based) approach taking seven meteorological variables as input data was developed based on the back propagation (BP) algorithm for detecting heavy precipitation. Apart from the surface meteorological variables of temperature, pressure and relative humidity, the model has also adopted other information such as day-of-year, hour-of-day and GNSS-derived zenith total delay and precipitable water vapor (PWV) as input variables. The feasibility of using these variables for developing the BP-NN-based model was elaborated by conducting the feature analysis of the seven input variables. In addition, the criterion for selecting a proper size of training sample was also briefly investigated by studying the impact and sensibility of the sample lengths in the model. The proposed model was developed using a sample size of an 8-year (2010–2017) period in the summer at a pair of co-located GNSS/weather stations−HKSC-KP in Hong Kong. The use of a long-term data is to “reliably” capture the characteristics of the selected variables. The detection results for the summer months in 2018 and 2019 were then compared against corresponding precipitation records to valid the effectiveness of the newly proposed model. Results of the correct detection and false alarm rates were 94.5 % and 20.8 %, respectively, which were significant improvements compared with the existing models.

Security enhancement of 2-D DIM codes using 4 × 1 NOR logic based on FISO

Security enhancement and bandwidth increase are requirements of ultrafast future optical code division networks that also minimise the latency at nodes without distressing the traffic performance. In OCDMA systems, eavesdropper tries to breach the optical code, and encoded/encrypted data in order to get correct code word of legitimate user. For security enhancement, an ultra high speed 4 \(\times\) 100 Gbps two dimensional Diagonal identity matrix (2D-DIM) code and four input single output (FISO) all optical logic gate with private key encryption is proposed and its performance in terms of security is analyzed. Expressions for synchronous and asynchronous transmissions are derived for proposed work and it is perceived that asynchronous transmission has better security. Further performance/security analysis is carried out for different scenarios such as with/without FISO, with 1D-DIM/2D-DIM codes, using 4 \(\times\) 1 AND gate/NOR gate in terms of correct code detection rate (CCDR), max. eye amplitude, Received Q factor, Signal to noise ratio at different launched power levels for legitimate user and eavesdropper. Eavesdropper attacked the proposed system but due to FISO layering, private key encryption, and 2D-DIM codes, cannot get acceptable level of CCDR. To the best of author’s knowledge, proposed system is ultra high speed with enhanced security and no reported studies have investigated security enhancement at this much ultra high speed.

Extraction of road boundary from MLS data using laser scanner ground trajectory

Abstract Various means of extracting road boundary from mobile laser scanning data based on vehicle trajectories have been investigated. Independent of positioning and navigation data, this study estimated the scanner ground track from the spatial distribution of the point cloud as an indicator of road location. We defined a typical edge block consisting of multiple continuous upward fluctuating points by abrupt changes in elevation, upward slope, and road horizontal slope. Subsequently, such edge blocks were searched for on both sides of the estimated track. A pseudo-mileage spacing map was constructed to reflect the variation in spacing between the track and edge blocks over distance, within which road boundary points were detected using a simple linear tracking model. Experimental results demonstrate that the ground trajectory of the extracted scanner forms a smooth and continuous string just on the road; this can serve as the basis for defining edge block and road boundary tracking algorithms. The defined edge block has been experimentally verified as highly accurate and strongly noise resistant, while the boundary tracking algorithm is simple, fast, and independent of the road boundary model used. The correct detection rate of the road boundary in two experimental data is more than 99.2%.

Grape stem detection using regression convolutional neural networks

Automation of grapevine agricultural tasks, e.g., harvesting, requires reliable methods for detecting the exact cutting points of the grape bunches. Dynamically changing vineyard environments, differences between plant varieties, illumination, occlusion, color similarities, and varying contrast make the detection of the grapes’ stems in unstructured environments difficult. In this work, a grape stem detection methodology in images is proposed, towards introducing an autonomous grape harvesting robot (ARG), as an affordable and consistent alternative to the time-consuming specialized work of an experienced harvester. For this purpose, a regression convolutional neural network (RegCNN) is applied for executing a stem segmentation task. Twelve Convolutional Neural Network (CNN) model architectures derived by the combination of three different feature learning sub-networks with four meta-architectures, are investigated. For the first time, stem detection is tackled as a regression problem in a way to alleviate the imbalanced data phenomenon that may occur in vineyard images. In order to justify the effectiveness of the RegCNN models, the same CNN architectures are tested in a typical classification (ClaCNN) setup. Comparative results involving two datasets with different characteristics reveal that the regression models outperform the classification ones. Grape bunches stems are detected with an Intersection-over-Union (IU) performance of up to 98.18% with RegCNNs, before post-processing optimization. Moreover, by applying a Genetic Algorithm (GA)-based parameter tuning mechanism, optimized post-processing parameters lead to an improved IU accuracy of up to 98.90% for the UNET_MOBILENETV2 model with acceptable real-time performance. Compared to other similar methodologies, the proposed method provides higher correct stem detection rates in unconstrained and highly changing environments, e.g., vineyards, and thus it is appropriate for robust real-time stem identification towards facilitating the agricultural tasks executed by a robot harvester.

The utility of Google Trends as a tool for evaluating flooding in data‐scarce places

AbstractGoogle Trends (GT) offers a historical database of global internet searches with the potential to complement conventional records of environmental hazards, especially in regions where formal hydrometeorological data are scarce. We evaluate the extent to which GT can discern heavy rainfall and floods in Kenya and Uganda during the period 2014 to 2018. We triangulate counts of flood searches from GT with available rainfall records and media reports to build an inventory of extreme events. The Spearman rank correlation (ρ) between monthly mean search interest for flooding and monthly Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) rainfall totals was ρ = +0.38 (p < 0.005) for Kenya and ρ = +0.64 (p < 0.001) for Uganda. Media reports of flooding were used to specify a threshold of detectability to give the same overall frequency of floods based on GT search interest. When the GT search index threshold was set at ≥15 and ≥29, the correct detection rate was 75% and 64% within a five‐day window of known flood events in Kenya and Uganda, respectively. From these preliminary explorations we conclude that GT has potential as a proxy data source, but greater skill may emerge in places with larger search volumes and by linking to historical information about environmental hazards at sub‐national scales. Wider applicability of the GT platform might be possible if there is greater transparency about how Google algorithms determine topics.

Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge.

Adopting effective techniques to automatically detect and identify small drones is a very compelling need for a number of different stakeholders in both the public and private sectors. This work presents three different original approaches that competed in a grand challenge on the “Drone vs. Bird” detection problem. The goal is to detect one or more drones appearing at some time point in video sequences where birds and other distractor objects may be also present, together with motion in background or foreground. Algorithms should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds, nor being confused by the rest of the scene. In particular, three original approaches based on different deep learning strategies are proposed and compared on a real-world dataset provided by a consortium of universities and research centers, under the 2020 edition of the Drone vs. Bird Detection Challenge. Results show that there is a range in difficulty among different test sequences, depending on the size and the shape visibility of the drone in the sequence, while sequences recorded by a moving camera and very distant drones are the most challenging ones. The performance comparison reveals that the different approaches perform somewhat complementary, in terms of correct detection rate, false alarm rate, and average precision.

Computer-aided skin cancer diagnosis based on a New meta-heuristic algorithm combined with support vector method

Skin cancer has grown significantly over the past decades, and the importance of its initial treatment is increasing day by day. This study aims to use a computer-aided diagnosis automatic system for the exact diagnosis of cancerous cases. In the present study, after applying pre-processing operations including contrast enhancement, image thresholding, and mathematical morphology for highlighting the important areas, feature extraction based on 20 different features has been applied. Then, for decreasing the system complexity, a new improved version of the world cup optimization algorithm is utilized for the features pruning. After optimal selection of the features, the injected into a support vector machine as a classifier to determine the cancerous areas. Experimental results are compared by different new algorithms including the classic SVM method, hybrid optimized neural networks based on gray wolf optimizer and particle swarm optimization algorithm, and also convolutional neural network. Results obtained for skin lesions images from two different databases indicate that the proposed method has higher efficiency than other published methods, demonstrating even better performance than the well-known classification method, the convolutional neural networks. The proposed method presents the highest correct detection rate - 92.64 for ACS images and 87.5 for ISIC images with very low false acceptance rates (4.41 % and 9 % for ACS and ISIC images, respectively) and even less false rejection rates, this is, 2.94 % on ACS images and 3.5 % on ISIC images. These results prove that the proposed method may be reliably used to diagnose skin cancer through dermoscopy images.

SAFE: A Novel Microwave Imaging System Design for Breast Cancer Screening and Early Detection-Clinical Evaluation.

SAFE (Scan and Find Early) is a novel microwave imaging device intended for breast cancer screening and early detection. SAFE is based on the use of harmless electromagnetic waves and can provide relevant initial diagnostic information without resorting to X-rays. Because of SAFE’s harmless effect on organic tissue, imaging can be performed repeatedly. In addition, the scanning process itself is not painful since breast compression is not required. Because of the absence of physical compression, SAFE can also detect tumors that are close to the thoracic wall. A total number of 115 patients underwent the SAFE scanning procedure, and the resultant images were compared with available magnetic resonance (MR), ultrasound, and mammography images in order to determine the correct detection rate. A sensitivity of 63% was achieved. Breast size influenced overall sensitivity, as sensitivity was lower in smaller breasts (51%) compared to larger ones (74%). Even though this is only a preliminary study, the results show promising concordance with clinical reports, thus encouraging further SAFE clinical studies.

A Plane Extraction Approach in Inverse Depth Images Based on Region-Growing.

Planar surfaces are prevalent components of man-made indoor scenes, and plane extraction plays a vital role in practical applications of computer vision and robotics, such as scene understanding, and mobile manipulation. Nowadays, most plane extraction methods are based on reconstruction of the scene. In this paper, plane representation is formulated in inverse-depth images. Based on this representation, we explored the potential to extract planes in images directly. A fast plane extraction approach, which employs the region growing algorithm in inverse-depth images, is presented. This approach consists of two main components: seeding, and region growing. In the seeding component, seeds are carefully selected locally in grid cells to improve exploration efficiency. After seeding, each seed begins to grow into a continuous plane in succession. Both greedy policy and a normal coherence check are employed to find boundaries accurately. During growth, neighbor coplanar planes are checked and merged to overcome the over-segmentation problem. Through experiments on public datasets and generated saw-tooth images, the proposed approach achieves 80.2% CDR (Correct Detection Rate) on the ABW SegComp Dataset, which has proven that it has comparable performance with the state-of-the-art. The proposed approach runs at 5 Hz on typical 680 × 480 images, which has shown its potential in real-time practical applications in computer vision and robotics with further improvement.

Introduced a new method for enhancement of intrusion detection with random forest and PSO algorithm

AbstractAs computer networks expand, attacks and intrusions into these networks have increased. In addition to firewalls and other intrusion prevention equipment, other systems, such as IDS (Metrics), are designed to provide enhanced security in computer systems, including the purpose of monitoring intrusive and intrusive activities. Intrusive allocation system can be considered effective if the high intrusion rate is slightly misleading, and in this article a new way to classify it is abnormal (infiltration) in the host or network. UNSW‐NB15 and KDD‐Cup'99 Datasets Introducing Random Forest and PSO algorithm. In this paper, training data and label data used with the random forest algorithm. After creating a random forest algorithm, provide test data. We use the data stored in train step, which is actually a copy of the data, so that when performing the test step, the same training data can be compared with categorize using a PSO algorithm. In in order to show the accuracy of the proposed method, an example of the confusion matrix formed in the code that showed performance of all methods and modes studied is compared based on accuracy and time that the PSO algorithm has always been able to take less time, which is quite acceptable and predictable. Improves correct diagnosis of correct detection rate in that report was 75.94% and in the proposed method in this article it reached 97%. With the proposed method, learning speed has been greatly increased and accuracy is acceptable.

The prevalence of Vickers' ligament in Madelung's deformity: a retrospective multicentre study of 75 surgical cases.

In a retrospective multicentre study, we aimed to correlate clinical factors and findings on plain radiographs and MRI with the intraoperative presence of Vickers’ ligament in Madelung’s deformity. We screened the records, in which the absence or presence of Vickers’ ligament was affirmatively indicated, of 75 consecutive operated extremities in 58 patients. In 83% a Vickers’ ligament was observed intraoperatively. The whole bone Madelung type (as opposed to the distal type) and a distal radial notch were independent, significant predictors for the presence of the ligament. The correct Vickers detection rate using MRI was 85% of the 27 cases for which MRI was available. Thus, the MRI was a good but not perfectly reliable modality. We conclude that Vickers’ ligament is present in the majority but not all cases with Madelung deformity. We advise that patients with a more severe type of Madelung’s deformity and a distal radial notch should be monitored closely.Level of evidence: IV

Combining Machine Learning and Dynamic Time Wrapping for Vehicle Driving Event Detection Using Smartphones

The detection of driving events could be useful for reducing accidents, fleet management and insurance premiums etc. Currently, top of the range vehicles and large fleets employ expensive driver monitoring systems. However, most drivers do not have access to such systems. The required monitoring platform would have to deliver the required performance while also being affordable and accessible. A candidate with considerable promise is the smartphone with sensors built-in that could be exploited for the detection of driving events. However, to date it has not been possible to achieve the required correct, missed and false detection rates in addition to the computational efficiency for real-time operations. This paper proposes a novel bagging tree and dynamic time warping (DTW) integrated algorithm for the detection of driving events employing acceleration and orientation data from a smartphone's low cost three-axis accelerometers and gyroscopes. The bagging tree-based machine learning algorithm provides the initial maneuver detection results, as well as the location of the event start and end points. Event detection is then achieved by calculating the similarity of the results predicted through the bagging tree algorithm with the corresponding templates extracted from the experience datasets, while also applying a number of constraints to verify the calculated results. Field test results show that the proposed integrated algorithm is superior to the state-of-the-art, achieving a high correct detection accuracy of 97.5%, a low missed detection of 2.5% and a false detection rate of 2.9%. The corresponding results for the best alternative candidate method are 90.2%, 9.8% and 11.7%. Furthermore, the improvement in computational efficiency offered by our proposed approach is three to more than ten times greater than that of the other state-of-the-art algorithms.

Tomato Leaf Disease Identification and Detection Based on Deep Convolutional Neural Network

Deep convolutional neural network (DCNN) requires a lot of data for training, but there has always been data vacuum in agriculture, making it difficult to label all existing data accurately. Therefore, a lightweight tomato leaf disease identification network supported by Variational auto-Encoder (VAE) is proposed to improve the accuracy of crop leaf disease identification. In the lightweight network, multi-scale convolution can expand the network width, enrich the extracted features, and reduce model parameters such as deep separable convolution. VAE makes full use of a large amount of unlabeled data to achieve unsupervised learning, and then uses labeled data for supervised disease identification. However, in the actual model deployment and production environment, VAE doesn’t require additional calculation and storage consumption, because it is not used in the calculation of the application phase. Compared with the classification network that only uses labeled data, the generalization effect and identification accuracy of this proposed method are enhanced. Especially in the case of fewer labeled samples, the identification accuracy has increased from 56.13% to 78.03%, and in the case of many labeled samples, the identification accuracy also shows a rise. We have fully confirmed the effectiveness of the lightweight network and VAE enhancement strategy: the correct detection rate of disease category by this method is 94.17%, and only 0.42% of the diseased leaves are misidentified as healthy leaves; the correct detection rate of healthy leaves is 98.27%, and only 1.73% of healthy leaves are misidentified as diseased leaves.

Canopy segmentation and wire reconstruction for kiwifruit robotic harvesting

Kiwifruits are commercially grown on sturdy support structures such as T-bars and pergolas. Wires are widely used in modern agriculture as an important material for supporting T-bars. It may lead to damage to kiwifruit harvesting end-effector or robot when accessing fruits occluded by branches or wires. Additional development to segment calyxes, branches, and wires will help to achieve higher-level picking strategies. DeepLabV3+ was adopted to segment the fruit calyx, branch, and wire in this work. A method of discrete wire pixels reconstruction was then developed on Progressive probabilistic Hough transform (PPHT) to help sense distribution of the wire. Lines that didn’t meet the constraints, i.e., angle or distance between the lines, were regarded as noise and eliminated. There were 327 images divided into training (261) and testing (66) sets, where the training set was augmented to 1566 images. The dataset was heavily imbalanced where the pixels of calyx, branch, and wire were much fewer than background pixels. For the imbalanced kiwifruit canopy image segmentation, it was proven that the uniform weights assignation method outperformed the median frequency weights. In terms of backbone, ResNet-101 achieved IoUs (intersection over union) of 0.686, 0.709, and 0.424 for calyx, branch, and wire, respectively, and the highest mIoU (mean IoU) of 0.694. It took about 210.0 ms to process a resolution of 512 × 341 pixels image, which could be acceptable for the kiwifruit harvesting robot. The PPHT achieved an correct detection rate of 92.4%, and was competitive in processing time of 6.4 ms/image. Canopy image segmentation can provide a basis for guiding the harvesting end-effector to pick kiwifruits safely, thus improving the harvesting success rate and reducing on-orchard costs.

Positive Predictive Value and Correct Detection Rate of 18F-rhPSMA-7 PET in Biochemically Recurrent Prostate Cancer Validated by Composite Reference Standard.

The objective of this retrospective study was to assess the detection rate (DR), positive predictive value (PPV), and correct detection rate (CDR) of 18F-rhPSMA-7 PET/CT in biochemical recurrence (BCR) of prostate cancer (PCa) after radical prostatectomy (RP) using composite validation. Methods:18F-rhPSMA-7 PET/CT scans of patients with BCR between July 2017 and June 2018 were retrospectively reviewed. All suspicious lesions were recorded. The reference standard was histopathology or combinations of histopathology, imaging, or prostate-specific antigen (PSA) follow up, defined as composite reference standard. DR was calculated as the proportion of PSMA PET-positive patients to all patients independent of the reference standard, whereas the CDR was the percentage of patients who had at least 1 true-positive PSMA PET lesion localized that corresponded with the reference standard. The PPV was defined as the proportion of patients who had true-positive to all positive findings. The correlation between DR and patient characteristics was evaluated. Results: A total of 532 patients with a median PSA level of 0.97 ng/mL (interquartile range: 0.41-2.46 ng/mL) were included. Of these, 162 patients had composite follow-up at a median duration of 5.6 mo (range: 1.1-14.2 mo). The proportion of patients who had no lesion visualized on PET/CT, localized disease, and any distant metastases (M1) were 20%, 43%, and 37%, respectively. PET DR among all patients was 80%. On a per-patient basis, the PPV of 18F-rhPSMA-7 PET/CT in the composite cohort was 88%, and the CDR was 70%. The PPV in the histopathology-proven cohort was 91%, and the CDR in this subgroup was 73%. In patients with PSA levels ≥ 1 ng/mL the DR and PPV were 90% and 91%, respectively, resulting in a CDR of 82%. In patients with PSA levels < 1 ng/mL, the DR and PPV were 69% and 85%, respectively, resulting in a CDR of 59%. There was a significant positive correlation between 18F-rhPSMA-7 PET/CT detection efficacy and stratified PSA levels (P = 0.005), as well as PSA nadir after prostatectomy (P < 0.001). Conclusion:18F-rhPSMA-7 PET/CT offers high PPV in BCR after RP. Its CDR is dependent on the prescan PSA value with excellent CDR in patients with PSA ≥ 1 ng/mL.

Automatic breast cancer detection based on optimized neural network using whale optimization algorithm

AbstractBreast cancer is the second deadliest type of cancer. Early detection of breast cancer can considerably improve the effectiveness of treatment. A significant early sign of breast cancer is the mass. However, separating the cancerous masses from the normal portions of the breast tissue is usually a challenge for radiologists. Recently, because of the availability of high‐accuracy computing, computer‐aided detection systems based on image processing have become capable of accurately diagnosing the various types of cancers. The main purpose of this study is to utilize a powerful image segmentation method for the diagnosis of cancerous regions through mammography, based on a new configuration of the multilayer perceptron (MLP) neural network. The most popular method for minimizing the errors in an MLP neural network is backpropagation. However, this method has certain drawbacks, such as a low convergence speed and becoming trapped at the local minimum. In this study, a new training algorithm based on the whale optimization algorithm is proposed for the MLP network. This algorithm is capable of solving various problems toward the current algorithms for the analyzed systems. The proposed method is validated on the Mammographic Image Analysis Society database, which contains 322 digitized mammography images, and the Digital Database for Screening Mammography, which contains approximately 2500 digitized mammography images. To assess the detection performance of the proposed system, the correct detection rate, percentage of identification with false acceptance, and percentage of identification with false rejection were evaluated and compared using various methods. The results indicate that the proposed method is highly efficient and yields significantly better accuracy compared with other methods.

Back propagation neural network analysis for the detection of explosives based on tagged neutron

A system for detecting explosives in walls based on the tagged neutron method was established. An associated particle neutron generator ING-27 developed by the All-Russian Research Institute of Automatics (VNIIA) is used as the neutron source, two yttrium lutetium silicate (LYSO) detectors are used for the γ detector, and a silicon detector is used as the α detector. The α-γ coincidence spectra of 300 g ammonium nitrate and TNT samples placed behind 10 cm concrete wall were measured. A neural network algorithm was applied to analyze the data. Through fine selection of time windows of α-γ coincidence spectra, the counts of full-energy peak of N, C and O elements and their proportions are selected as the input eigenvectors. The neural network is trained by the experimental data obtained by this system. Through training, eight groups of test data consisting of 32 γ-ray spectra were identified, and a 98.7% of correct detection rate was achieved.

Fault Diagnosis of Multi-level Principal Component Space Based on High-Dimensional Feature Representation

Due to the influence of space equivalent representation and pattern composition, traditional principal component analysis (PCA) is faced with challenges in identifying small faults. This paper proposes a fault diagnosis method is proposed based on multi-levels principal component space based on high-dimensional feature representation. Firstly, based on the original PCA, the dimensions are expanded first and then reduced, so that the information that cannot be expressed in the original space is fully expressed. This method further divides the principal element space based on the eigenvalues, and projects the occurrence of the event and the size of the identification abnormality according to the projection to different sub-spaces. Compared with the usual fault detection methods, simulations verify that this algorithm can effectively measure the level of faults and improve the correct detection rate of minor faults.