Adaptive Threshold Algorithm Research Articles

An adaptive thresholding algorithm for porosity measurement of additively manufactured metal test samples via X-ray computed tomography

Abstract If additively manufactured metal parts are to be used as performance critical components in the aerospace and other high-value industries, then non-destructive methods for measuring the porosity of these parts are required; X-ray computed tomography (XCT) is a promising instrument for this measurement task. One disadvantage of using XCT for this purpose is the presence of artefacts in XCT data of high-density materials (aluminium, titanium, steel and Inconel). These artefacts are problematic for segmentation algorithms that are required for porosity measurement. In this work we propose an adaptive thresholding algorithm for segmenting XCT data. The algorithm is specifically designed to overcome the influence of beam hardening (cupping) artefacts that are typically observed when XCT scanning high-density metal parts. The algorithm is also designed to have as few as possible user-defined settings in order to minimise the influence the user has on the segmentation result. The results show that the algorithm is able to segment small voids in low contrast-to-noise ratio XCT data and that the algorithm is robust to cupping artefacts. The accuracy of the method is evaluated for a set of Inconel cubes approximately 10 mm × 10 mm × 10 mm in size (H × W × D), reference porosity measurements are made using Archimedes’ principle. The mean error and standard deviation of the XCT percentage porosity measurements evaluated by four different users are found to be: −0.38 ± 0.09%, 0.09 ± 0.09% and −0.23 ± 0.22% for samples with bulk porosities of 0.23 ± 0.28%, 1.42 ± 0.28% and 3.00 ± 0.28%, respectively.

The Smart Fall Detection Mechanism for Healthcare Under Free-Living Conditions

With the growing number of silver hair people, they cannot ignore the care system, fall is one of the important causes of death from accident injury. If the fall is not detected in time, the consequences may be very serious, even. The psychological haze caused by the injured leads to a reduction in activity. The care system includes a smartwatch to monitor physiological values and detect falls, a Beacon device for indoor positioning, and outdoor air quality sensors. And set up a cloud server in Amazon to act as a system hub, designed an APP on the Android platform to control location, physiology, medication status, and give timely reminders. In the smartwatch fall detection section, this study proposes an adaptive threshold algorithm based on fuzzy theory to determine the fall. When a fall occurs, Beacon immediately locates the caregiver position and via Wi-Fi sends packets containing the location of the fall and the identity of the caregiver to the server, and sends notifications to the caregiver mobile app through the server. In the experiment, the acceleration data of six male and six female subjects were collected during daily activities and falls, and then analyzed the difference in the acceleration value of different height and weight during fall. 93.75% Sensitivity and 97.5% Specificity. This system enables existing care providers to get more real-time information and feedback, thereby improving overall service quality and efficiency, reducing human costs and resource consumption.

Tcp Syn Flood Attack Detection and Prevention System using Adaptive Thresholding Method

Transmission Control Protocol Synchronized (SYN) flooding contributes to a major part of the Denial of service attacks (Dos) because of the easy to exploit nature of the TCP three way handshake mechanism. Attackers use this weakness to overflow the TCP queue of the server and make its re-sources consumed resulting it to be unavailable for the requests of legitimate users. So we are in need of a quick and precise defence mechanism to detect the TCP-SYN Flood attack. The main objective of the paper is to propose a detection and prevention mechanism of the TCP-SYN flood attack using adaptive thresholding. Adaptive threshold algorithm (ATA) is used to calculate dynamic threshold .Thus this algorithm helps to overcome the limitations of static thresholding like high false positive ratio and also alert users after violation of the threshold calculated by adaptive thresholding algorithm. The result of the suggested mechanism is very effective in the detection and prevention of the TCP SYN flood attack using adaptive thresholding algorithm.

An Insulator in Transmission Lines Recognition and Fault Detection Model Based on Improved Faster RCNN

Insulators are critical electric components in transmission lines. Recognizing insulators and detecting the faults timely and accurately is essential for maintaining the safety and stability of transmission lines. Traditional methods have low accuracy and poor applicability in insulator recognition and fault detection. An insulator recognition and fault detection model was proposed in the article aiming at improving the insulator recognition and fault detection accuracy. First, based on the faster region convolutional neural network (RCNN), the feature pyramid networks (FPNs) were used to improve the Faster RCNN model and locate the insulators with complex background image. Then, the target area was clipped to remove the redundant background noise, and the hue, saturation, and value (HSV) color space adaptive threshold algorithm was applied for image segmentation due to the influence of light, background noise, and shooting angle. Finally, line detection, image rotation, and vertical projection were used to finish the insulator fault detection. The experimental results show that the proposed insulator recognition and fault detection model can recognize the insulators and detect fault types with better accuracy and achieve a mean average precision (mAP) of 90.8% for glass insulators and 91.7% for composite insulators on the testing dataset. Additionally, the proposed method meets the intelligent inspection of insulator faults in transmission lines and has good engineering application value.

Moving object detection of assembly components based on improved background subtraction algorithm

In the automatic assembly of mechanical components, it is difficult to guarantee the quality of assembly image acquisition caused by the change of assembly environment. Firstly, the color space is compared and analysed, and histogram equalization is used to preprocess the image to reduce the impact of image brightness on subsequent processing. Then, based on the texture features of the image, an image reconstruction idea from coarse to fine is created, and an image representation method from macro to micro is established to suppress the pseudo texture and noise texture in image processing. On this basis, an adaptive threshold algorithm based on the target distance is proposed to improve the detection accuracy of the assembly target. Experimental results show that the proposed algorithm can significantly improve the detection accuracy of moving objects in assembly video frames.

Framework for Machine Learning of CT and PET Radiomics to Predict Local Failure after Radiotherapy in Locally Advanced Head and Neck Cancers.

Context:Cancer Radiomics is an emerging field in medical imaging and refers to the process of converting routine radiological images that are typically qualitatively interpreted to quantifiable descriptions of the tumor phenotypes and when combined with statistical analytics can improve the accuracy of clinical outcome prediction models. However, to understand the radiomic features and their correlation to molecular changes in the tumor, first, there is a need for the development of robust image analysis methods, software tools and statistical prediction models which is often limited in low- and middle-income countries (LMIC).Aims:The aim is to build a framework for machine learning of radiomic features of planning computed tomography (CT) and positron emission tomography (PET) using open source radiomics and data analytics platforms to make it widely accessible to clinical groups. The framework is tested in a small cohort to predict local disease failure following radiation treatment for head-and-neck cancer (HNC). The predictors were also compared with the existing Aerts HNC radiomics signature.Settings and Design:Retrospective analysis of patients with locally advanced HNC between 2017 and 2018 and 31 patients with both pre- and post-radiation CT and evaluation PET were selected.Subjects and Methods:Tumor volumes were delineated on baseline PET using the semi-automatic adaptive-threshold algorithm and propagated to CT; PyRadiomics features (total of 110 under shape/intensity/texture classes) were extracted. Two feature-selection methods were tested for model stability. Models were built based on least absolute shrinkage and selection operator-logistic and Ridge regression of the top pretreatment radiomic features and compared to Aerts' HNC-signature. Average model performance across all internal validation test folds was summarized by the area under the receiver operator curve (ROC).Results:Both feature selection methods selected CT features MCC (GLCM), SumEntropy (GLCM) and Sphericity (Shape) that could predict the binary failure status in the cross-validated group and achieved an AUC >0.7. However, models using Aerts' signature features (Energy, Compactness, GLRLM-GrayLevelNonUniformity and GrayLevelNonUniformity-HLH wavelet) could not achieve a clear separation between outcomes (AUC = 0.51–0.54).Conclusions:Radiomics pipeline included open-source workflows which makes it adoptable in LMIC countries. Additional independent validation of data is crucial for the implementation of radiomic models for clinical risk stratification.

Monitoring coal seam fires in Xinjiang using comprehensive thermal infrared and time series InSAR detection

ABSTRACT The combustion of underground coal seams has important effects on the national economy and strategic energy security of countries, and damages the environment, ecology, vegetation, and water resources. Xinjiang, China, is one of the most serious areas of coalfield fires in the world, and it is difficult for any single remote sensing detection method to meet the practical requirements for accurate detection of fire areas. In order to detect coalfield areas in Xinjiang more accurately and reliably, a detection method that integrates thermal infrared and radar remote sensing anomaly is proposed: The mono-window algorithm is used to retrieve the Land Surface Temperature (LST) using images from the Land Remote-Sensing Satellite System (Landsat) 8, the Adaptive Edge Threshold Algorithm (AETA) is used to extract the data characterized by LST anomalies, and Small Baseline Subsets Interferometric Synthetic Aperture Radar (SBAS-InSAR) is used to obtain the land surface subsidence information from Sentinel-1A images. Through the overlay analysis of the above-mentioned LST and subsidence information, the extraction of possible coal fire areas in the Jiangjun Gobi area of Xinjiang is realized. As well as according to the characteristic that underground coal fires melt snow in winter, areas where coal fires are unlikely to occur are excluded using the natural, true-colour images of Landsat 8. Finally, the proposed method is verified using the characteristics of the time series cumulative subsidence of the land surface in areas where coal fires are likely to occur, and by examining the coupling between subsidence velocity and anomalies in LST data. The results show that the proposed method can overcome the shortcomings of single-factor remote sensing detection to a certain extent, and has the ability to detect fire areas more accurately.

Application of Adaptive Threshold Algorithm with Selected Modified Parameters for the Detection of Flooding Based Denial-of-Service (DoS) Attack in Mobile AdHoc Network

Mobile AdHoc Networks (MANET) were self- organizing networks formed without pre-installed infrastructure. Nodes in these networks extensively relied on intermediate nodes to communicate with the destination node. Due to the limited network and host resources, Denial-of-Service (DoS) attacks were the major problem faced by MANET. Flooding based DoS attacks aimed to overwhelm certain resources which resulted in destabilizing an entire network which further denying the access of services to legitimate users. SYN flooding attack was a flooding attack launched from the transport layer of TCP/IP protocol stack in which the attacker forwarded a prodigious number of spoofed SYN packets to the victim node in order to overflow its back log queue. Fixed Threshold Algorithm (FTA) or Adaptive Threshold Algorithm (ATA) was a commonly used technique for detecting these attacks in the network in which an alarm was raised whenever the number of SYN packets increased abnormally. But these algorithms were suffered from a higher false positive rate (FPR) and lower accuracy.There as on for these limitations was that network traffic statistics were updated regularly during normal traffic conditions as well as for attack traffic. In order to overcome these limitations,a modified version of the Adaptive Threshold Algorithm was proposed.Based on the comprehensive evaluation using DARPA data set,it was shown that the present work could successfully detect flooding attacks with higher accuracy and lower false positive rate.

Deep Learning for Detecting and Classifying Ocean Objects: Application of YoloV3 for Iceberg–Ship Discrimination

Synthetic aperture radar (SAR) plays a remarkable role in ocean surveillance, with capabilities of detecting oil spills, icebergs, and marine traffic both at daytime and at night, regardless of clouds and extreme weather conditions. The detection of ocean objects using SAR relies on well-established methods, mostly adaptive thresholding algorithms. In most waters, the dominant ocean objects are ships, whereas in arctic waters the vast majority of objects are icebergs drifting in the ocean and can be mistaken for ships in terms of navigation and ocean surveillance. Since these objects can look very much alike in SAR images, the determination of what objects actually are still relies on manual detection and human interpretation. With the increasing interest in the arctic regions for marine transportation, it is crucial to develop novel approaches for automatic monitoring of the traffic in these waters with satellite data. Hence, this study aims at proposing a deep learning model based on YoloV3 for discriminating icebergs and ships, which could be used for mapping ocean objects ahead of a journey. Using dual-polarization Sentinel-1 data, we pilot-tested our approach on a case study in Greenland. Our findings reveal that our approach is capable of training a deep learning model with reliable detection accuracy. Our methodical approach along with the choice of data and classifiers can be of great importance to climate change researchers, shipping industries and biodiversity analysts. The main difficulties were faced in the creation of training data in the Arctic waters and we concluded that future work must focus on issues regarding training data.

Sand Dune Dynamics Exploiting a Fully Automatic Method Using Satellite SAR Data

This work presents an automatic procedure to quantify dune dynamics on isolated barchan dunes exploiting Synthetic Aperture RADAR satellite data. We use C-band datasets, allowing the multi-temporal analysis of dune dynamics in two study areas, one located between the Western Sahara and Mauritania and the second one located in the South Rayan dune field in Egypt. Our method uses an adaptive parametric thresholding algorithm and common geospatial operations. A quantitative dune dynamics analysis is also performed. We have measured dune migration rates of 2–6 m/year in the NNW-SSE direction and 11–20 m/year NNE-SSW for the South Rayan and West-Sahara dune fields, respectively. To validate our results, we have manually tracked several dunes per study area using Google Earth imagery. Results from both automatic and manual approaches are consistent. Finally, we discuss the advantages and limitations of the approach presented.

WITHDRAWN: Fault diagnosis of three-phase electrically-excited synchronous motor by using adaptive threshold algorithm

Abstract Stator winding inter-turn short circuit faults and single-phasing faults are the major causes of failures of Electrically-Excited Synchronous Motor. This abnormality progressively grow faults leads to be complete damage of the machine. Hence in order to improve the sustainability of the system and increase the life of the motor suitable condition monitoring technique are necessary to identification of fault occurrence. In this context, this paper introduce the detection and phase identification of the turn-level short circuit faults in electrically excited synchronous machines. To detect and identify the faulty phases an algorithm is proposed based on a wavelet based multi-resolution analysis along with adaptive threshold for motor operated under different operating conditions. Stationary wavelet transform is employed to get the 3-ɸ currents fault residues and then discrete wavelet transform is employed to extract the disturbance information from the 3-ɸ residue currents. In order to find the fault location and phase identification fault index and 3-ɸ energies are compared with adaptive thresholds. Under different operating conditions finally, the algorithm is tested with practical data for single-phasing and various levels of inter-turn short circuit faults. By using acquired practical results the validity and successfulness of a proposed algorithm is clearly determined.

Research on steel barrel flattened seam recognition based on machine vision

Aiming at the problems of low efficiency and poor accuracy in manually identifying the flattened weld seam. The method of combining machine vision technology with multi-thread and multi-process is proposed, and the detection and recognition system of flattened weld seam is designed. OTSU adaptive threshold algorithm combined with Canny operator edge detection method is used for image segmentation. The probabilistic Hough transform algorithm is used to extract straight lines to identify flattened weld seam. OpenCV function library and Python are used to implement image processing algorithm, and PyQt5 is used to design human-computer interface to monitor the status of weld seam detection in real time. Meanwhile, a processing pool for parallel processing of recognition algorithm is established, and Modbus communication and image acquisition are realized by multi-thread programming. The performance of multi-core CPU is fully utilized. The experimental results show that the system meets the design requirements, has the characteristics of small amount of calculation and accurate identification, improves the processing efficiency, and solves the practical production problems.

Oil Spill Detection using Sentinel-1 Multitemporal Data in Offshore Karawang

Oil spill is a serious problem that could lead to economic and ecological losses, both in the short and long term. On July 12, 2019, there occurred an oil leakage around YYA-1 oil platform of Pertamina Hulu Energi Offshore North West Java (PHE ONWJ), located off the northern coast of Karawang, Java Sea. This incident has caused the death of fishes and marine animals, damage to coral reefs, mangroves, and seagrass beds, and several health problems of coastal communities. Therefore, it is necessary to map and monitor oil spills, so that actions can be taken to prevent the spread of oil spills. This study aims to map the distribution of oil spills in Karawang sea using multitemporal Sentinel-1 data from July to September 2019. The detection is carried out using the adaptive thresholding algorithm combined with manual interpretation. The result shows that the oil spills spread around Karawang sea from YYA-1 platform to Sedari Village and there are oil spills spreading from the Central Plant F/S platform. The oil spills tend to shift westward from July to September 2019. This shifting is supposed to be influenced by current and wave factors that were dominant moving westward at that time. Based on data processing, it was found that the oil spill area from July to September was respectively 24.79 km2, 20.05 km2, and 27.12 km2.

Automatic cancer detection on digital histopathology images of mid-gland radical prostatectomy specimens.

Purpose: Automatic cancer detection on radical prostatectomy (RP) sections facilitates graphical and quantitative surgical pathology reporting, which can potentially benefit postsurgery follow-up care and treatment planning. It can also support imaging validation studies using a histologic reference standard and pathology research studies. This problem is challenging due to the large sizes of digital histopathology whole-mount whole-slide images (WSIs) of RP sections and staining variability across different WSIs. Approach: We proposed a calibration-free adaptive thresholding algorithm, which compensates for staining variability and yields consistent tissue component maps (TCMs) of the nuclei, lumina, and other tissues. We used and compared three machine learning methods for classifying each cancer versus noncancer region of interest (ROI) throughout each WSI: (1)conventional machine learning methods and 14 texture features extracted from TCMs, (2)transfer learning with pretrained AlexNet fine-tuned by TCM ROIs, and (3)transfer learning with pretrained AlexNet fine-tuned with raw image ROIs. Results: The three methods yielded areas under the receiver operating characteristic curve of 0.96, 0.98, and 0.98, respectively, in leave-one-patient-out cross validation using 1.3million ROIs from 286 mid-gland whole-mount WSIs from 68 patients. Conclusion: Transfer learning with the use of TCMs demonstrated state-of-the-art overall performance and is more stable with respect to sample size across different tissue types. For the tissue types involving Gleason 5 (most aggressive) cancer, it achieved the best performance compared to the other tested methods. This tool can be translated to clinical workflow to assist graphical and quantitative pathology reporting for surgical specimens upon further multicenter validation.

Flooding Attack Detection and Mitigation in SDN with Modified Adaptive Threshold Algorithm

Flooding Attack Detection and Mitigation in SDN with Modified Adaptive Threshold Algorithm

Assessing the effects of body weight on subchondral bone formation with quantitative 18F-sodium fluoride PET.

The aim of this study was to quantify subchondral bone remodeling in the elbows, hands, knees, and feet using volumetric and metabolic parameters derived from 18F-sodium fluoride positron emission tomography (NaF-PET) and to assess the convergent validity of these parameters as an index of joint degeneration and preclinical osteoarthritis. A retrospective analysis was conducted in 34 subjects (32 males, 2 females) with metastatic bone disease who underwent full-body NaF-PET/CT scans. An adaptive contrast-oriented thresholding algorithm was applied to segment NaF-avid regions in the bilateral elbows, hands, knees, and feet of each subject, and metabolically active volume (MAV), maximum standardized uptake value (SUVmax), mean metabolic volumetric product (MVPmean), and partial volume-corrected MVPmean (cMVPmean) of the segmented regions were calculated. Global parameters for MAV, SUVmax, MVPmean, and cMVPmean were defined as the sum of the corresponding values in all the joints of a subject. Inter-rater reliability was determined with Lin's concordance correlation, and associations of global values with subject body weight and age were assessed with Pearson correlation and Spearman correlation analyses. Inter-rater reliability was observed to be the highest in SUVmax (ρc = 0.99), followed by MVPmean (ρc = 0.96), cMVPmean (ρc = 0.93), and MAV (ρc = 0.93). MAV, MVPmean, and cMVPmean were observed to significantly increase with weight (all p < 0.0001) determined by Pearson correlation. In addition, Spearman rank-order analysis demonstrated a significant correlation between SUVmax and weight in addition to MAV, MVPmean, and cMVPmean and weight (all p < 0.01). No significant association between age and any PET parameter was observed. These preliminary data demonstrate the feasibility and reliability of assessing bone turnover at the joints using quantitative NaF-PET. Our findings corroborate the fact that biomechanical factors including mechanical loading and weight-bearing are contributors to osteoarthritis disease progression.

Research on 3D Facial Expression Simulation Technology

In order to generate realistic facial animation, this paper uses depth learning object detection technology to detect the three wrinkles of human face, and then the adaptive threshold algorithm is used to extract the wrinkle curves, finally applies realistic wrinkle animation to the virtual face model. In the aspect of expression animation simulation, based on MPEG-4 standard, a database of expression parameters covering six major expressions has been established, which divide the human face into four main animation units and other auxiliary animation units. According to the displacement of animation unit between neutral expression and other expressions, the facial bone points of virtual model are driven to move, thus realizing realistic facial expression animation.

An Adaptive Thresholding Algorithm-Based Optical Character Recognition System for Information Extraction in Complex Images

Extracting texts from images with complex backgrounds is a major challenge today. Many existing Optical Character Recognition (OCR) systems could not handle this problem. As reported in the literature, some existing methods that can handle the problem still encounter major difficulties with extracting texts from images with sharp varying contours, touching word and skewed words from scanned documents and images with such complex backgrounds. There is, therefore, a need for new methods that could easily and efficiently extract texts from these images with complex backgrounds, which is the primary reason for this work. This study collected image data and investigated the processes involved in image processing and the techniques applied for data segmentation. It employed an adaptive thresholding algorithm to the selected images to properly segment text characters from the image’s complex background. It then used Tesseract, a machine learning product, to extract the text from the image file. The images used were coloured images sourced from the internet with different formats like jpg, png, webp and different resolutions. A custom adaptive algorithm was applied to the images to unify their complex backgrounds. This algorithm leveraged on the Gaussian thresholding algorithm. The algorithm differs from the conventional Gaussian algorithm as it dynamically generated the blocksize to apply threshing to the image. This ensured that, unlike conventional image segmentation, images were processed area-wise (in pixels) as specified by the algorithm at each instance. The system was implemented using Python 3.6 programming language. Experimentation involved fifty different images with complex backgrounds. The results showed that the system was able to extract English character-based texts from images with complex backgrounds with 69.7% word-level accuracy and 81.9% character-level accuracy. The proposed method in this study proved to be more efficient as it outperformed the existing methods in terms of the character level percentage accuracy.

Empirical correlation for spray half cone angle in plain-jet airblast atomizers

Plain-jet airblast atomizers are widely used in industrial applications. The literature contains numerous papers on Sauter mean diameter, however, there is no estimation method available for spray cone angle, SCA, which derivation is the primary goal of this study. Four distinct, practical model liquids were analyzed: distilled water, diesel oil, light heating oil, and crude rapeseed oil. The atomizing pressure and liquid preheating temperature were varied in the range of 0.3–2.4 bar and 25–85 °C, respectively. This latter parameter enabled a wide and continuous liquid kinematic viscosity investigation range of 0.33–44.2 mm2/s. The resulting sprays were imaged at various shutter speeds for proper edge detection. An adaptive thresholding algorithm was developed in Matlab software environment to calculate SCA. The methodology is discussed in detail to facilitate the re-implementation of this technique since there is no generally accepted method for SCA measurement. SCA inversely varied with liquid density and followed a power law with the air-to-liquid mass flow ratio; however, the derived expression also performed well by replacing air-to-liquid mass flow ratio by either Mach number or momentum flux ratio. A simple empirical equation was derived, which allows the estimation of SCA of airblast atomization in a wide parameter range within a 3.5% deviation. The measured results were evaluated in the light of high-speed camera images in the vicinity of the nozzle; it was found that increased liquid jet breakup length decreases SCA while intense ligament formation increases it.

Flooding Attack Detection and Mitigation in SDN with Modified Adaptive Threshold Algorithm

Flooding Attack Detection and Mitigation in SDN with Modified Adaptive Threshold Algorithm