High Accuracy Time Research Articles

Convolutional Neural Networks for the Distinction of Subdural and Epidural Hematoma

Background:Subdural and epidural hematoma are common after brain injury by the external mechanical force. The classification between subdural and epidural hematoma is mostly reckoned on the neurosurgeons’ experience in medical images. Our work proposed a model based on Convolutional Neural Networks (CNN) to improve the diagnosis accuracy of subdural hematoma and epidural hematoma. Methods: According to the inclusion criteria, totally 200 patients with subdural hematoma and epidural hematoma from the West China Hospital were enrolled. The computerized tomography (CT) images of these patients were preprocessed by mirroring, noise enhancement, increment, graying and convolution, generating 9000 original CT images. These images were divided into raining set 8100, verification set 450 and test set 450, creating the Visual Geometry Group16(VGG16) Convolutional Neural Networks. The basic model can be obtained through training Neural Network Model with data from training set. The optimal model can be obtained by modifying parameters of the basic model and optimizing it with data from validation set. With data from test set, the accuracy of the optimal model can be evaluated. Lastly, with methods such as Accuracy, Precision, Recall, F1-measure, the accuracy of this model can be evaluated. Results: The classification accuracy of the validation set on the model is 0.984 and the accuracy of CT images from the third-party organizations is 0.900. It takes 5.6 seconds averagely for the model to evaluate the image.Conclusion: The classification model has a high accuracy and short prediction time, indicating the feasibility of applying Artificial Intelligence Aided Diagnosis in practice.

Blockchain Data Secure Transmission Method Based on Homomorphic Encryption.

To ensure the security of data transmission and recording in Internet environment monitoring systems, this paper proposes a study of a secure method of blockchain data transfer based on homomorphic encryption. Blockchain data transmission is realized through homomorphic encryption. Homomorphic encryption can not only encrypt the original data, but also ensure that the data result after decrypting the data is the same as the original data. The asymmetric encrypted public key is collected by Internet of things (IoT) equipment to realize the design of blockchain data secure transmission method based on homomorphic encryption. The experimental results show that the accuracy of the first transmission is as high as 88% when using the transmission method in this paper. After several experiments, the transmission accuracy is high by using the design method in this paper. In the last test, the transmission accuracy is still 88%, and the data transmission effect is relatively stable. At the same time, compared to the management method used in this article, the transfer method used in this paper is more reliable than the original transfer method and is not prone to data distortion. It can be seen that this method has high transmission accuracy and short transmission time, which effectively avoids the data tampering caused by too long time in the transmission process.

Efficient Detection of Abrupt Transitions Using Statistical Methods

The rapid increment of technological advancements in the field of multimedia stream has piled up data production and consumption in cyberspace in the past two decades. It has prompted a swift increase in data transmission volume and repository size. Video is the most consumed data type on the internet. So, retrieval of selected video clips from the extra-large database of videos is extremely complex. The video shot boundary detection (SBD) is used for retrieval of desired video clips. It also is the fundamental step in video processing, which also was found important for applications like video browsing and indexing. The SBD handles the identification of abrupt and gradual transitions in the video database. In this paper, the statistical methods have implemented to detect the abrupt cuts. This benefitted the advantage of less complexity. The experiments are performed on TRECVID 2007 dataset, and the results obtained with high accuracy in less computational time.

Novel quantification of regional fossil fuel CO2 reductions during COVID-19 lockdowns using atmospheric oxygen measurements.

It is not currently possible to quantify regional-scale fossil fuel carbon dioxide (ffCO2) emissions with high accuracy in near real time. Existing atmospheric methods for separating ffCO2 from large natural carbon dioxide variations are constrained by sampling limitations, so that estimates of regional changes in ffCO2 emissions, such as those occurring in response to coronavirus disease 2019 (COVID-19) lockdowns, rely on indirect activity data. We present a method for quantifying regional signals of ffCO2 based on continuous atmospheric measurements of oxygen and carbon dioxide combined into the tracer “atmospheric potential oxygen” (APO). We detect and quantify ffCO2 reductions during 2020–2021 caused by the two U.K. COVID-19 lockdowns individually using APO data from Weybourne Atmospheric Observatory in the United Kingdom and a machine learning algorithm. Our APO-based assessment has near–real-time potential and provides high-frequency information that is in good agreement with the spread of ffCO2 emissions reductions from three independent lower-frequency U.K. estimates.

Hybrid Approach for Botnet Detection Using K-Means and K-Medoids with Hopfield Neural Network

In the last few years, a number of attacks and malicious activities have been attributed to common channels between users. A botnet is considered as an important carrier of malicious and undesirable briskness. In this paper, we propose a support vector machine to classify botnet activities according to k-means, k-medoids, and neural network clusters. The proposed approach is based on the features of transfer control protocol packets. System performance and accuracy are evaluated using a predefined data set. Results show the ability of the proposed approach to detect botnet activities with high accuracy and performance in a short execution time. The proposed system provides 95.7% accuracy rate with a false positive rate less than or equal to 3%.

Measuring the refractive index of scintillation crystal with a Mach-Zehnder interferometer

The refractive index of the scintillation crystal is a key parameter in the design of Positron Emission Tomography (PET) devices. However, existing methods to measure the refractive index always suffer from problems such as the complexity of optical path adjustment, long time cost, or high equipment consumption. To overcome these problems, we propose a method that can obtain the refractive index of the scintillation crystal with high accuracy in real time. In this method, we employ the Mach-Zehnder interferometer to generate the interference pattern when one beam of light passes through the scintillation crystal, which encodes the value of refractive index into the width of pattern. To obtain the width of interference pattern, we calculate the width pixels of dark/bright stripes in pattern with threshold, respectively, and finally get the average number of pixels of the pattern; this strategy can eliminate the coherent interference signal and random noise effectively. The optical path need not adjust during the whole measurement. Thus, the refractive index of scintillation crystals can be measured with reliability and efficiency. To validate the effectiveness of the proposed method, we measure different batches of BGO crystal and Ce:LYSO crystal samples. The results show that the proposed method can measure refractive indices with high accuracy and high efficiency, providing a reliable crystal refractive index measurement procedure for the PET detector module design. The proposed method is also suitable for refractive index measurements of transparent materials in visible light bands.

In vitro measurement of hepatic flow distribution in Fontan vascular conduits: Towards rapid validation techniques

Fontan operation is the last stage of single-ventricle surgical reconstructions that connects superior and inferior vena cava (SVC, IVC) to the pulmonary arteries. The key design objectives in total cavopulmonary connections (TCPC) are to achieve low power loss (PL) and balanced hepatic flow distribution (HFD). Computational fluid dynamics (CFD) played a pivotal role in pre-surgical design of single-ventricle patients. However, the clinical application of current CFD techniques is limited due to their complexity, high computational time and untested accuracy for HFD prediction. This study provides a performance assessment of computationally low-cost steady Reynolds-Averaged Navier-Stokes (RANS) k-ɛ turbulent models for simulation of Fontan hemodynamics. The performance is evaluated based on prediction accuracy for three clinically important Fontan hemodynamic indices: HFD, PL and total pulmonary flow split (TPFS). For this purpose, a low-cost experimental technique is developed for rapid quantification of Fontan performance indices. Experiments and simulations are performed for both an idealized and a complex 3D reconstructed patient-specific TCPC. Time-averaged flow data from phase contrast MRI was used as the boundary conditions for the patient-specific model. For the idealized model, different SVC/IVC flow ratios corresponding to different cardiac outputs and Reynolds’ numbers were examined. This study revealed that steady RANS k-ɛ models are able to estimate the Fontan hemodynamic indices with acceptable accuracy within minutes. Among these, standard k-ɛ two-layer was found to deliver the best agreement with the in vitro data with an average error percentage of 1.7, 2.0 and, 3.9 for HFD, TPFS and, PL, respectively for all cases.

GA-GRGAT: A novel deep learning model for high-speed train axle temperature long term forecasting

Long-term axle temperature prediction plays a significant role in train condition assessment and daily maintenance. However, most of methods make predictions for short-term conditions. In this paper, a method named GA-GRGAT is introduced that uses GAT and GAN to forecast the long-term axle temperature. In the proposed method, a GRGAT framework is used as a spatiotemporal fusion in temperature prediction. The GAN network with the GRGAT framework is used to construct a temporal conditional sequence after analyzing the periodic variation of the axle temperature, which can fuse the historical axle temperature information to improve the long-term prediction accuracy of the GA-GRGAT model. Our method in Python software and using the actual high-speed trains datasets in spring and summer. We using MAE, RMSE, MAPE, PCC to evaluate the accuracy of prediction. The accuracy of the GA-GRGAT is more than 90% on long-term predictions (1 day), and more than 80% on super long-term predictions (2 week). The GA-GRGAT method outperforms and is more accurate than the classical forecasting methods such as GRU, GOAMLP, DCNN, SVR and HA. In addition, the cost time of the proposed method is less than 5 min, which meets the requirements of high accuracy and long time.

Solution for Model Parameter Optimization and Prediction of Next-Generation Device DC Characteristics

We present a novel method to predict the next-generation device characteristics and model optimization solutions for the process design kit. We demonstrate the next-generation prediction methodology from the creation of device characteristics to the development of a compact model. The proposed method achieves high accuracy and reduction in development turnaround time.

High Order Semi-implicit WENO Schemes for All-Mach Full Euler System of Gas Dynamics

In this paper, we propose high order semi-implicit schemes for the all Mach full Euler equations of gas dynamics. Material waves are treated explicitly, while acoustic waves are treated implicitly, thus avoiding severe CFL restrictions for low Mach flows. High order accuracy in time is obtained by semi-implicit temporal integrator based on the IMEX Runge-Kutta (IMEX-RK) framework. High order in space is achieved by finite difference WENO schemes with characteristic-wise reconstructions adapted to the semi-implicit IMEX-RK time discretization. The schemes are proven to be asymptotic preserving and asymptotically accurate as the Mach number vanishes. Besides, they can well capture discontinuous solutions in the compressible regime, especially for two dimensional Riemann problems. Numerical tests in one and two space dimensions will illustrate the effectiveness of the proposed schemes.

An Enhanced Differential Protection Scheme for LVDC Microgrid

The low-voltage dc (LVDC) microgrid possesses numerous benefits and their penetration in the power system has increased rapidly in recent years. However, the detection of faults in the LVDC microgrid is a challenging issue due to the large magnitude of fault currents and fault-level variation in the microgrid. The performance of the recent current and its derivative-based protection scheme is limited in case of faults in the islanding mode of operation, different microgrid topologies, varying distributed generations (DGs) penetration, and against the measurement noise. This article presents an enhanced differential protection scheme for LVDC microgrid integrated with multiple DGs and storage. The differential current and its first derivative are processed through the decision tree (DT) algorithm for fault detection and the K-nearest neighbor (KNN) technique is utilized for fault classification. The robustness of the proposed protection scheme is tested for different fault types and fault conditions with variation in microgrid topology and operating conditions. The impact of the intermittent and volatile nature of the DGs, the presence of measurement noise, and assessment during external faults and critical no-fault cases have been investigated. The proposed scheme is tested on the MATLAB/ SIMULINK and validated on the Typhoon HIL platform for the assessment of real-time performance. The test results show that the proposed scheme can detect and classify faults with high accuracy and faster response time and, thus, can be a potential candidate for providing dependable protection measures for LVDC microgrids.

Intellectual system for automated determination of the quality of natural stones surfaces processing

This automation of determination of the quality of natural stone surfaces processing is a relevant problem. It provides an intellectual system for automated determination of the quality of processing surfaces of natural stones (ISADQSS), which allows rapid assessment of the quality of stone surfaces, including roughness, with high accuracy and quick action in automatic mode and real time. The measurement result is independent of the humidity and cleanliness of the outer surface. The root mean square error of the proposed ISADQSS does not exceed 5%, the time to determine the value of the roughness is not over 2 s. ISADQSS is based on the principles of synergetic integration of various technical automation devices with different properties – artificial neural networks (ANN) (in the case of their implementation in the form of neuroprocessors), as well as the so-called registrar of main drive currents (RMDC), which is used as a sensor sensitive to changes in the rubbing force of the stone-cutting tool depending on changes in the roughness value of the machined surface. The proposed ISADQSS is an innovative and promising development that combines such advantages as high accuracy and speed, versatility and ease of use.

New Methods for Predicting Strain Demand of Arctic Gas Pipelines across Permafrost under Frost Heave Displacement

With increasing gas resource development in the Arctic region, gas pipeline installations in permafrost regions are becoming important. Frost heave of pipeline foundation soils may occur when a chilled gas pipeline passes through unfrozen areas with frost-susceptible soils. The stress and strain behaviors caused by the differential frost heave will directly affect the safety of the pipeline. A nonlinear finite element model (FEM) computing the mechanical responses of the buried gas pipeline subjected to frost heave load was established and successfully validated with the results of a large-scale indoor pipe-soil interaction experiment carried out in Caen in France. Utilizing C# language and object-oriented visual programming techniques, a new customized parametric strain calculation software was developed. The effects of pipe diameter, pipe wall thickness, pipe internal pressure, and peak soil resistance on the longitudinal strain of X60, X70, and X80 steel pipes have been investigated quantitatively. For the first time, a fitting semiempirical equation and trained backpropagation neural network (BPNN) for predicting pipeline strain demand subjected to frost heave load were proposed based on 2688 groups of FEM results. The comparison results have proved their high accuracy and lower running time cost. The proposed new methods can be applied in the strain-based pipeline design and safety evaluation of pipelines in service. It is in the hope of supplementing existing theory and identifying new approaches for arctic gas pipeline installations.

A Human-Machine Interface Based on an EOG and a Gyroscope for Humanoid Robot Control and Its Application to Home Services

The human-machine interface (HMI) has been studied for robot teleoperation with the aim of empowering people who experience motor disabilities to increase their interaction with the physical environment. The challenge of an HMI for robot control is to rapidly, accurately, and sufficiently produce control commands. In this paper, an asynchronous HMI based on an electrooculogram (EOG) and a gyroscope is proposed using two self-paced and endogenous features, double blink and head rotation. By designing the multilevel graphical user interface (GUI), the user can rotate his head to move the cursor of the GUI and create a double blink to trigger the button in the interface. The proposed HMI is able to supply sufficient commands at the same time with high accuracy (ACC) and low response time (RT). In the trigger task of sixteen healthy subjects, the target was clicked from 20 options with ACC of 99.2% and RT 2.34 s. Furthermore, a continuous strategy that uses motion start and motion stop commands to create a certain robot motion is proposed to control a humanoid robot based on the HMI. It avoids the situation that combines some commands to achieve one motion or converts the certain motion to a command directly. In the home service experiment, all subjects operated a humanoid robot changing the state of a switch, grasping a key, and putting it into a box. The time ratio between HMI control and manual control was 1.22, and the number of commands ratio was 1.18. The results demonstrated that the continuous strategy and proposed HMI can improve performance in humanoid robot control.

Lumped parameter thermal network for thermal analysis of a rotor-excited axial flux switching machine with electromagnetic-thermal design

In this paper, a three-dimensional (3-D) lumped parameter thermal network (LPTN) model is presented for the first time for a rotor-excited axial-field flux-switching permanent magnet (RE-AFFSPM) machine. The 3-D LPTN predicts the steady-state temperature of different parts in various operating conditions. To enhance the LPTN accuracy and comprehensiveness, (i) the convection heat transfer in the internal and external areas, as well as radiation from the end-windings, (ii) core material anisotropic thermal conductivity, (iii) the equal thermal conductivity of the winding in the slot, and (iv) contact thermal resistances are all considered. Heat transfer coefficients are obtained mathematically to be applicable for the RE-AFFSPM machines with different parameters. A 3-D finite element method (FEM) is established to calculate the electromagnetic losses and thermal analysis with high accuracy. Eddy current losses in the stator core, rotor core, permanent magnets (PMs), and carriers, along with hysteresis losses in the stator and rotor cores, are calculated by 3-D FEM then coupled to the thermal analysis to predict the temperature distribution. By comparing the temperature results of the 3-D LPTN and 3-D FEM at various speeds, air–gap lengths, loading levels, and simultaneous variation of the current density and speed, the performance of the proposed 3-D LPTN is further investigated and verified. Results indicate that by the proposed 3-D LPTN, components temperature can be approximated with high accuracy in a lesser time than the 3-D FEM.

A new real-time trajectory generation method modifying trajectory based on trajectory error and angular speed for high accuracy and short machining time

A computationally efficient FIR-filtering based tool-path (trajectory) modification method, which simultaneously realizes remarkable trajectory error reduction, vibration avoidance, and short machining time, is presented in this paper. Conventional trajectory generation in NC units causes trajectory error by using smoothing filters for limiting acceleration and avoiding vibration of the machines, and this trajectory error is often too large for practical applications. Therefore, a novel trajectory generation method is presented in this paper to remarkably reduce the trajectory error by modifying the trajectory commanded by G-codes on the basis of the trajectory error and angular speed. In order to realize the trajectory modification method, three key components, (i) p-corresponding method, (ii) ω-smoothing filter, and (iii) modification gain function, are developed in this study. The p-corresponding method is required to stably evaluate the trajectory error, while the other two components are used to compute appropriate modification gains for arbitrary trajectories. The proposed trajectory modification method is completed by integrating the components (i) to (iii), and it is verified utilizing a commercial machine tool. It is confirmed that average trajectory error is reduced remarkably by the proposed method without increasing machining time or sacrificing vibration avoidance by the smoothing filter. In particular, the trajectory errors at circular arcs are eliminated almost completely, e.g., the average trajectory error is reduced significantly by about 80% for a trajectory consisting of several circular arcs and corners.

Application of Chain Beam Constraint Model in numerical design Bistable compliant mechanisms

Bistable compliant mechanism is a monolithic part and jointless in the structure, is utilized due to saving energy, precious in operation, and reducing maintenance costs. This mechanism work based on the compression and tension of the flexural beam. Most calculation methods assist the mechanism's characteristics to have challenges because of the nonlinear behavior of the structure. This paper employs the CBCM (Chained Beam Constraints Model) method to analyze and evaluate Bistable compliant mechanisms. The flexural beam of the mechanism is divided into many segments for evaluating the compliant mechanism behavior. This method is verified with the finite element method and the results show insignificant errors. CBCM assists in the design of the compliant Bistable mechanism with high accuracy in a short time.

SRS: Spatial-tagged radio-mapping system combining LiDAR and mobile-phone data for indoor location-based services

One of the most challenging issues in radio received signal strength (RSS)-based localization systems is the generation and distribution of a radio map with a coordinate system linked with spatial information in a large indoor space. This study proposes a novel spatial-tagged radio-mapping system (SRS) that effectively combines the heterogeneous properties of LiDAR and mobile phones to simultaneously perform both spatial and radio mappings. The SRS consists of synchronization, localization, and map building processes, and enables real-time spatial and radio mapping. In the synchronization process, the distance range, motion data, and radio signals obtained through the LiDAR and mobile phone are collected in nodal units according to the sensing time. In the localization process, a feature variance filter is used to control the number of features generated from LiDAR and estimate the positions at which the nodes are generated in real time according to the motion data and radio signals. In map building, the estimated positions of the nodes are used to extract spatial and radio maps by using a unified location coordinate system. To ensure mobility, the SRS is manufactured in the form of a backpack supporting LiDAR and a mobile phone; the usefulness of the system is experimentally verified. The experiments are performed in a large indoor shopping mall with a complex structure. The experimental results demonstrated that a common coordinate system could be used to build spatial and radio maps with high accuracy and efficiency in real time. In addition, the field applicability of the SRS to location-based services is experimentally verified by applying the constructed radio map to well-known fingerprinting algorithms using the heterogeneous mobile phones.

DBGC: Dimension-Based Generic Convolution Block for Object Recognition.

The object recognition concept is being widely used a result of increasing CCTV surveillance and the need for automatic object or activity detection from images or video. Increases in the use of various sensor networks have also raised the need of lightweight process frameworks. Much research has been carried out in this area, but the research scope is colossal as it deals with open-ended problems such as being able to achieve high accuracy in little time using lightweight process frameworks. Convolution Neural Networks and their variants are widely used in various computer vision activities, but most of the architectures of CNN are application-specific. There is always a need for generic architectures with better performance. This paper introduces the Dimension-Based Generic Convolution Block (DBGC), which can be used with any CNN to make the architecture generic and provide a dimension-wise selection of various height, width, and depth kernels. This single unit which uses the separable convolution concept provides multiple combinations using various dimension-based kernels. This single unit can be used for height-based, width-based, or depth-based dimensions; the same unit can even be used for height and width, width and depth, and depth and height dimensions. It can also be used for combinations involving all three dimensions of height, width, and depth. The main novelty of DBGC lies in the dimension selector block included in the proposed architecture. Proposed unoptimized kernel dimensions reduce FLOPs by around one third and also reduce the accuracy by around one half; semi-optimized kernel dimensions yield almost the same or higher accuracy with half the FLOPs of the original architecture, while optimized kernel dimensions provide 5 to 6% higher accuracy with around a 10 M reduction in FLOPs.

Fast and simplified determination of PCA and aromatic carbon content of treated distilled aromatic extract (TDAE) by NMR.

Aromatic oils obtained during lubricant production (DAE) have high value as rubber extenders in tire manufacturing, but they have high carcinogenic potential due to the content of polycyclic aromatic compounds (PCAs). Legislation on PCA content requires additional treatment to reach treated oils (TDAE) with a PCA content lower than 3% according to the IP 346 method. IP 346 is a highly time-consuming and high uncertainty method, and several proposals have tried to replace it, but nowadays, there is no standard alternative. In this work, an extensive collection of samples covering a broad PCA content were obtained and characterized by physical properties, NMR, and aromatic and PCA content. Several correlations were tested to establish an optimum procedure to estimate the aromatic and the PCA content according to the requirement of high accuracy and low time and effort. The combination of several properties does not improve the accuracy of the correlation, and simpler equations were preferred. Integrated spectra appear as an acceptable characterization method as NMR percent of the total aromatic proton and polycyclic aromatic proton correlates satisfactory with the number of aromatic carbons and PCA content, respectively. The refractive index yields the best results for the correlation to PCA content. Obtained deviations compare favorably with methods previously described in the literature and with the uncertainty involved in the experimental method. They can be considered adequate methods to analyze such magnitudes routinely.