Cascade Algorithm Research Articles

Two-grid algorithm for a system of singularly perturbed reaction-diffusion equations on Shishkin mesh

A system of two coupled singularly perturbed reaction-diffusion equations is considered. A cascadic two-grid algorithm of high accuracy based on a uniform with respect to small parameters convergent difference scheme for such problem has been developed. To increase the accuracy of the difference solution by an order, the Richardson extrapolation method was applied. The results of some numerical experiments are discussed.

Drowsiness Detection Based on Facial Landmark and Uniform Local Binary Pattern

When driving a vehicle, it is often challenging for someone to force his condition to keep driving even though in sleepy condition, thus causing a traffic accident. One of the characteristics of drowsy drivers is the eyes are closed for a certain period. This research proposes a system to detect drowsiness, thus can alert the drowsy driver. The first step is to detect the face using a Funnel-structured cascade algorithm. And then extract the facial landmark features on the face to get the eyes location. The features of eyes are extracted by using a Uniform Local Binary Pattern (ULBP) and the Eyes Aspect Ratio (EAR). EAR is the distance between points at eye landmarks. After the features have been extracted, the system classifies the eyes, whether closed or open by using Support Vector Machine (SVM) method. The system calculates the percentage of eye closure (PERCLOS) to detect drowsiness. Based on the experimental results, the proposed method yields the best accuracy of 95.5% and the optimal value of PERCLOS in drowsiness detection is greater than or equal to 60% with a period of 20 frames.

Vision system for detection of defects on apples using hyperspectral imaging coupled with neural network and Haar cascade algorithm

The article is devoted to the development of algorithms for detecting defective apples transported on a roller conveyor using a vision system. In developing the algorithms, the possibility of classifying various regions of interest (intact and damaged by rot, scab, codling moth, as well as the conveyor) by the principal component method was investigated. When choosing the optimal spectral region for cluster analysis, spectrograms obtained in various spectral ranges, including Vis-NIR (400–1000 nm), NIR (780–1000 nm), and Vis (400–780 nm) were used. The PCA method showed that for the successful classification of the conveyor area, intact, decayed and damaged by the codling moth, it is necessary to use spectrograms in the Vis-NIR range. To classify these ROIs, it was proposed to use a direct distribution neural network with two hidden layers of 128 and 64 layers, respectively, the “relu” activation function in the hidden layers and the “softmax” activation function in the output layer. The optimal network configuration was determined experimentally. This configuration showed a classification accuracy of 0.847 on a test sample of 6,000 apples. Since the samples of spectrograms of scab and stem regions do not differ, for their classification in parallel with the neural network, it was proposed to use the Haar cascade classifier trained on 2000 two-dimensional images of apples in the visible region containing scab and stem regions. The classification accuracy was at least 0.95. The developed algorithm is intended for use in the robotic sorting of apples.

Driver Drowsiness Detection System using Machine Learning Algorithms

Road crashes are the most common forms of accidents and deaths worldwide, and the significant reasons for these accidents are usually drunken, drowsiness and reckless behaviour of the driver. According to the World Health Organization, road traffic injuries have risen to 1.25 billion worldwide, which makes driver drowsiness detection a major potential area to avert numerous sleep-induced road accidents. This project proposes an idea to detect drowsiness using machine learning algorithms, hence alarming the driver in real-time to prevent a collision. The model uses the Haar Cascade algorithm, along with the OpenCV library to monitor the real-time video of the driver and to detect the eyes of the driver. The system uses the Eye Aspect Ratio (EAR) concept to determine if the eyes are open or closed. We also feed a data-set file consisting of the facial features data-points to train the machine learning algorithm. The model inspects each frame of the video, which helps to recognize the state of the driver. Furthermore, a Raspberry Pi single-board computer, combined with a camera module and an alarm system, facilitates the project to emulate a compact drowsiness detection system suitable for different automobiles.

RETRACTED ARTICLE: Video analytics for semantic substance extraction using OpenCV in python

With the rise of crimes all over the world, video surveillance is gaining more significance day by day. Presently, monitoring videos is done manually. If a crime occurs in a city, to find the sequence or event, it is necessary to play the entire video after which searching and processing needs to be done manually. Due to the lack of human resource, it is necessary to develop a new video analytics framework to perform higher level tasks in semantic content extraction. Manual processing of video is wasteful, one-sided, and more expensive thereby limiting the searching abilities. So it is necessary to model a framework for extracting objects from the video data. A Semantic Substance Extraction model using OpenCV is proposed for organizing video resources. Video analytics for semantic substance extraction is an effort to use real time, publicly available data to improve the prediction of the moving objects from the video streams. Background separation and Haar Cascade algorithms are used in this model to perform video analytics. Usage of this method has achieved a detection precision of 84.11% and a recall of 50.27%. These results are 78% faster than content extraction using existing fuzzy and neural methods.

Subband Maximum Eigenvalue Detection for Radar Moving Target in Sea Clutter

In this letter, a cascade algorithm combined subband decomposition with an eigenvalue-based detection scheme is proposed to detect moving targets in sea clutter for the radar system with short pulses. Using a discrete Fourier transform-modulated filter bank, on the one hand, subband decomposition can effectively suppress clutter as well as increase the coherent integration time. On the other hand, it transforms the scene where the target spectrum is separated from the clutter spectrum into the scene where the target spectrum overlaps with the clutter spectrum. In the target subband, the noncoherent method using amplitude difference is more favorable for detection due to the nonobvious phase difference caused by the overlap of the target spectrum and the clutter spectrum. Considering that the maximum eigenvalue can reflect the signal intensity and capture the signal correlations well, the maximum eigenvalue of the covariance matrix is adopted to discriminate the target from the clutter. Finally, the simulation results show that the proposed algorithm achieves superior performance.

Aircraft Trajectory Tracking Using Radar Equipment with Fuzzy Logic Algorithm

Radio-electronic means, including equipment for transmissions, radio-location, broadcasting, and navigation, allow the execution of various research missions and combat forces management. Determining the target coordinates and directing the armament towards them, obtaining and processing data about enemies, ensuring the navigation of ships, planes and outer atmospheric means, transmitting orders, decisions, reports and other necessary information for the armed forces; these are only some of the possibilities of radio-electronic technology. Fuzzy logic allows the linguistic description of the laws of command, operation and control of a system. When working with complex and nonlinear systems, it can often be observed that, as their complexity increases, there is a decrease in the significance of the details in describing the global behavior of the system. Even though such an approach may seem inadequate, it is often superior and less laborious than a rigorous mathematical approach. The main argument in favor of fuzzy set theory is to excel in operating with imprecise, vague notions. This article demonstrates the superiority of a fuzzy tracking system over the standard Kalman filter tracking system under the conditions of uneven accelerations and sudden change of direction of the targets, as well as in the case of failure to observe the target during successive scans. A cascading Kalman filtering algorithm was used to solve the speed ambiguity and to reduce the measurement error in real-time radar processing. The cascade filters are extended Kalman filters with controlled gain using fuzzy logic for tracking targets using radar equipment under difficult tracking conditions.

Decentralized optimal operation model for cooperative microgrids considering renewable energy uncertainties

An increasing number of microgrids (MGs) with high penetration of renewables are being integrated into the distribution system (DS). Multiple MGs as stakeholders in the future retail markets may sign a cooperation contract when faced with high uncertainties of renewable energies and complementary features among MGs. The optimal coordinated operation mechanism for the MGs would be essential. In this paper, we propose a decentralized optimal operation framework to coordinate the power exchange among MGs abiding by a cooperative contract based on the analytical target cascading (ATC) algorithm. Furthermore, to address the renewable energy uncertainties in the operation strategy of each MG, a two-stage adjustable robust optimization model is devised to coordinate the power exchange between the DS and MGs, the demand response, the output of controlled distributed generations (DGs), and the charging/discharging behavior of energy storage system (ESS). Then, the column and constraint generation method (CCG) is applied to solve the proposed robust optimization model. Comparative studies based on a DS with three typical MGs are performed to validate the effectiveness of the proposed methods.

Cascadic adaptive finite element method for nonlinear eigenvalue problem based on complementary approach

In this paper, a type of cascadic adaptive finite element method for nonlinear eigenvalue problem is proposed based on the complementary approach. In this new scheme, we only need to do some smoothing steps for the linearized boundary value problems on a series of adaptive finite element spaces and solve some nonlinear eigenvalue problems on a low dimensional space. Hence the efficiency can be improved since we do not need to solve the nonlinear eigenvalue problems on each adaptive space directly. Besides, the complementary error estimate for nonlinear eigenvalue problem will be introduced in our paper. This estimate can not only provide an accurate error estimate for the nonlinear eigenvalue problem but also provide the way to refine mesh and control the number of smoothing steps for the cascadic adaptive algorithm. Some numerical examples are presented to validate the efficiency of the proposed algorithm in this paper.

Neighbor Cell List Optimization in Handover Management Using Cascading Bandits Algorithm

Frequent handover is a key challenge in 5G Ultra-Dense Networks (UDN). In this paper, we show the significance of configuring Neighbor Cell List (NCL) in handover procedure. To cope with the high dynamic of UDN, we propose an online-learning method, namely the Cost-aware Cascading Bandits NCL configuration (CCB-NCL) algorithm, which applies the cascading model and Multi-Armed Bandits (MAB) theory to configure the efficient Neighbor Cell List (eNCL) and improves the handover performance by assisting the User Equipment (UE) to choose the optimal target Base Station (BS). We provide rigorous proof of regret bound to show the asymptotic convergence of the proposed CCB-NCL algorithm. The robustness and efficiency of the proposed algorithm are both demonstrated in different network scenarios, where varies BS densities, BS dynamic and network heterogeneity are considered respectively. In the simulation work, we reproduce two existing methods of configuring NCL in handover management, named dynamic threshold based solution and received signal strength based solution. In comparison with the existing solutions, the proposed algorithm can reduce the overlarge signaling cost and unnecessary delay in the preparation phase of handover procedure by significantly shortening the length of NCLs and reducing the number of scanned BSs. Extensive simulations are conducted in different scenarios to validate the robustness of the proposed algorithm and the results show that the proposed CCB-NCL algorithm is a superior approach to efficient handover management.

Cascading Failure Analysis Method of Avionics Based on Operational Process State

In the context of functional integration of avionics, the complex operational process interaction has increased the complexity of the cascading failure analysis, which is significant to evaluate the overall safety status and design rationality. In order to achieve a dynamic and dimensional evaluation of cascading failures, this paper proposes a safety analysis method based on operational process state, with an operational process-orientated hierarchical system functional framework established by means of the state machine. Then the cascading failure causation dynamic search algorithms and the cascading failure causation tree structure are designed respectively to describe the failure propagation in combination. Consequently, cascading failure propagation paths and minimum cut sets are generated automatically based on the search result. By using the aircraft integrated surveillance system as a research object, the effect and cause of cascading failure assessed in various failure scenarios have validated the effectiveness of the proposed method, and the comparison against the existing model based safety analysis methods demonstrates the higher flexibility and efficiency of the proposed method. The proposed method enables the dynamic and overall assessment of system safety status concentrating on the cascading failure utilizing the operational process state, and further enhances the systemization and automation level of the safety evaluation process in the early development phase.

Intelligent College Attendance System Using Image Tagging

In the paper, we have proposed a real-time attendance system using image tagging to overcome the wastage of time in queues for biometrics or face scanning, manual entry of attendance in the logbook and to overcome conventional manual attendance system to reduce cost and proxy attendance. Image tagging is the process of adding labels or keywords to the recognized faces or things within a certain picture. The image is processed using image segmentation and feature extraction to obtain faces and then the faces are tagged. Intelligent College Attendance system using Image tagging conducts regular attendance labeling and review tasks with a decrease in the management and control of human intervention plays a vital role in maintaining the attendance system. First, we capture an image of the whole class and stores the image in the database. In this proposed system, the faces are first detected using OpenCV's Haar cascade algorithm. The detected faces then undergo Principal Component Analysis and Local Binary Pattern algorithm to detect the student. The latest face detection and recognition technologies struggle to solve issues such as scaling, posture, lighting, variations, etc. The program proposed is designed to resolve pitfalls by providing features such as extracting of features, detection of features and analysis. We find a specific area, for instance, a classroom corner for installing the camera and checking device accuracy. The database will get automatically updated regarding the absence or presence of the student in the class.

Stochastically coordinated transmission and distribution system operation with large-scale wind farms

With the high penetration of renewable energies in modern power systems, deterministic coordination algorithms are facing two major problems: one is degradation in accuracy if fewer scenarios are utilized for uncertainty evaluation while second is the high computational time if a high number of scenarios are considered for better accuracy. In both cases, the efficiency of the algorithm is degraded. To solve these problems in coupled transmission system and distribution systems (TSDS), probabilistic coordination algorithms are adopted to solve with less effort. In this paper, a TSDS probabilistic coordination model is proposed to solve the coordinated security-constrained unit commitment problem. A mean and standard deviation matching based probabilistic analytical target cascading algorithm has been utilized for evaluation of TSDS coordination problem. Instead of solving each scenario as a separate problem, the proposed algorithm considers a single coordination problem with probabilistic characteristics as shared variables and hence, achieves fast convergence. Different case studies are performed to prove the efficacy of the proposed algorithm. Results verify that the proposed algorithm reduces computational time and resources for large-scale systems.

Nonlinear predictive filter based fault diagnosis of oxygen generation system by using electrolytic water in space station

The oxygen generation system using electrolytic water is one of the important systems in space station which supplies the oxygen for the astronauts from the condensate water, i.e., Sabatier reduction reaction water and urine treated water. During the operation of the space station, the normal operation of the system directly affects the safety of astronauts and the operating costs of the space station, so the fault diagnosis of the system has become a research hotspot. This paper systematically describes the fault diagnosis method of the oxygen generation system using electrolytic water, including the establishment of the fault mode and effects analysis, mathematical model of the key components and the estimation algorithm of unmeasured parameters. For the two direct discriminant indicators of the oxygen production and hydrogen production, because they are unmeasurable and their dynamic models are difficult to be established, this paper proposes a cascade algorithm of nonlinear predictive filtering and low-pass filter to solve the problem. Firstly, the oxygen and hydrogen production are estimated by the predictive filter. And then, the high frequency noise introduced by measurement error is eliminated when the oxygen and hydrogen production signals entered in a low-pass filter. Through the simulation analysis of the normal and fault mode, the correctness and effectiveness of the estimation algorithm are illustrated.

Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi

Driver’s drowsiness is one of the leading contributing factors to the increasing accidents statistics in Malaysia. Therefore, the design and development of driver drowsiness detection based on image processing using Raspberry Pi camera module sensor interfacing with Raspberry Pi 3 board are proposed in this paper. To achieve the aim of the research, the Haar Cascade Classifier algorithm is implemented for eyes and face detection whereas for eyes blink (open and close) detection, the Eye Aspect Ratio (EAR) algorithm is employed. From several experiments conducted on six recruited subjects, the findings revealed that the accuracy of Haar Cascade classifier to detect the eyes and faces was subjected to correct sitting position (head must facing to the camera) as well as the eyes must not be covered with glasses or shades. Meanwhile, the range of average EAR value detected by the system was between 0.141 (eyes closed) and 0.339 (eyes opened). In conclusion, the image processing-based Haar Cascade and EAR algorithms utilized on Raspberry Pi platform have been successfully executed. For future improvement, the current board can be replaced with Raspberry Pi Touch Screen to minimize the hardware setup and the physiological based analysis using alcohol and heart rate sensors can be added.

Credit Card Transaction Based on Face Recognition Technology

This paper proposes a method for credit card transaction system which will make use of face recognition and face detection technology, using Haar Cascade and GLCM algorithm. The main problem faced by credit card users is attack to lot of privacy issues such as credit card. This generally happens when users give their credit card number to unknown people or when the card is lost. So, we are proposing a system that will reduce the risk of credit card frauds. The system we are proposing will match the image of user’s face with dataset of respective user. A database will be maintained for authentication purpose. If the image matches, that means user is genuine and he will be allowed to proceed otherwise, the user will be denied to do the transaction.

Temporal Decomposition for Security-Constrained Unit Commitment

This paper proposes a temporal decomposition strategy to reduce the computation time of security-constrained unit commitment (SCUC). The novelty of this paper is twofold. The scheduling horizon is decomposed into multiple subhorizons. The concept of coupling intervals is introduced, and a set of auxiliary counting variables and logical expressions along with their equivalent linear models are formulated to handle intertemporal ramp constraints and minimum on/off times between consecutive subhorizons. An accelerated analytical target cascading (A-ATC) algorithm is developed to coordinate SCUC subproblems and find the optimal solution for the whole operation horizon in a distributed manner. An initialization strategy is presented to enhance the convergence performance of A-ATC. The proposed algorithm is tested on four test systems.

Investigation of the dual cascade algorithm in the diagnosis of antinuclear antibodies

AbstractBackgroundThe dual cascade algorithm which involves screening and confirmation of antinuclear antibodies (ANAs) by further reflex testing is widely used in the detection of ANAs. We aimed to investigate this algorithm which is commonly used in many laboratories.MethodsA total of 475 sera obtained from patients with a clinical suspicion of systemic autoimmune rheumatic diseases (SARDs) upon which three expert assessors agreed for interpretation in the indirect immunofluorescence (IIF) test were determined and tested by the line immunoassay (LIA) containing 16 antigens. The results of the tests were statistically compared and evaluated.ResultsIn 141 of the sera (29.7%), there was an agreement between ANA-IIF(+) and LIA(+) results. The overall agreement rate between the two tests for positivity and negativity only was 85.5% with a Cohen’s κ coefficient of 0.69. In 118 of these 141 sera (83.7%), pattern and associated ANA agreement was detected with an overall agreement rate of 80.6% and a Cohen’s κ coefficient of 0.57. The highest agreement between the pattern and associated ANAs was seen in centromere, dense fine speckled (DFS) and cytoplasmic reticular patterns. In these patterns, the rate of anti-centromere-associated protein B (CENP-B), anti-DFS and anti-antimitochondrial antibody M2 (anti-AMA-M2) antibodies were 93.4%, 92.3% and 66.7%, respectively.ConclusionsWe found an overall moderate agreement between IIF screening and LIA confirmation tests. However, the level of agreement varies according to the pattern type. The discrepancy in agreement rates may cause false reflex test requests. Our results highlight the need for collaboration between clinical and laboratory professionals in selected cases instead of the reflex testing approach.

1061. Decreased Utilization of Piperacillin–Tazobactam for Escherichia coli and Klebsiella Bacteremia due to Selective Susceptibility Reporting

BackgroundOver 2 million people in the United States are diagnosed with antibiotic-resistant infections annually. The Infectious Diseases Society of America (IDSA) recommends cascade reporting of antibiotic susceptibility data by the clinical microbiology laboratory as an intervention to decrease resistance, though this is based on low-quality evidence.MethodsWe conducted a retrospective study to assess the effect of cascade susceptibility reporting on prescribing practices and patient outcomes. A cascaded testing algorithm was executed wherein susceptibility data for piperacillin–tazobactam (PT) was suppressed from the susceptibility report if an organism was susceptible to ceftriaxone. Patients with positive monomicrobial blood cultures with non-ESBL Escherichia coli (E. coli) or Klebsiella isolates in blood cultures and receiving empiric PT were included. Data were collected one year prior and one year after cascading protocol implementation, and included patient demographics, length of stay (LOS), duration of antibiotics, time to de-escalation, and adverse events including acute kidney injury (AKI) and Clostridioides difficile infection (CDI).Results212 patients (108 pre-intervention and 104 post-intervention) were included. 87% of patients were de-escalated from PT pre-intervention, while 90% were deescalated post-intervention. Mean time to deescalation decreased from 30 hours before to 17 hours after cascade implementation (P = 0.02) (Figure 1). Median LOS decreased from 15 to 10 days following the intervention (P = 0.12). While the rate of AKI increased from 14 to 19% post-intervention (P = 0.89), the rate of CDI (2 vs. 2 patients) was comparable among both cohorts (P = 0.97) (Figure 2).ConclusionWhile cascade susceptibility reporting is recommended by the IDSA as a tool for antimicrobial stewardship, this recommendation has weak support due to paucity of data. In this study, we found that selective susceptibility reporting has the potential to decrease the use of PT and to reduce LOS in patients with E. coli and Klebsiella bacteremia. Further research to better identify patient populations most impacted by a cascade algorithm and its overall effectiveness as a stewardship tool is needed. Disclosures All authors: No reported disclosures.

OPU: An FPGA-Based Overlay Processor for Convolutional Neural Networks

Field-programmable gate array (FPGA) provides rich parallel computing resources with high energy efficiency, making it ideal for deep convolutional neural network (CNN) acceleration. In recent years, automatic compilers have been developed to generate network-specific FPGA accelerators. However, with more cascading deep CNN algorithms adapted by various complicated tasks, reconfiguration of FPGA devices during runtime becomes unavoidable when network-specific accelerators are employed. Such reconfiguration can be difficult for edge devices. Moreover, network-specific accelerator means regeneration of RTL code and physical implementation whenever the network is updated. This is not easy for CNN end users. In this article, we propose a domain-specific FPGA overlay processor, named OPU to accelerate CNN networks. It offers software-like programmability for CNN end users, as CNN algorithms are automatically compiled into executable codes, which are loaded and executed by OPU without reconfiguration of FPGA for switch or update of CNN networks. Our OPU instructions have complicated functions with variable runtimes but a uniform length. The granularity of instruction is optimized to provide good performance and sufficient flexibility, while reducing complexity to develop microarchitecture and compiler. Experiments show that OPU can achieve an average of 91% runtime multiplication and accumulation unit (MAC) efficiency (RME) among nine different networks. Moreover, for VGG and YOLO networks, OPU outperforms automatically compiled network-specific accelerators in the literature. In addition, OPU shows $5.35\times $ better power efficiency compared with Titan Xp. For a real-time cascaded CNN networks scenario, OPU is $2.9\times $ faster compared with edge computing GPU Jetson Tx2, which has a similar amount of computing resources.