Based on the two-dimensional （2D） system theory, an integrated predictive iterative learning control （2D-IPILC） strategy for batch processes is presented. First, the output response and the error transition model ...Based on the two-dimensional （2D） system theory, an integrated predictive iterative learning control （2D-IPILC） strategy for batch processes is presented. First, the output response and the error transition model predictions along the batch index can be calculated analytically due to the 2D Roesser model of the batch process. Then, an integrated framework of combining iterative learning control （ILC） and model predictive control （MPC） is formed reasonably. The output of feedforward ILC is estimated on the basis of the predefined process 2D model. By min- imizing a quadratic objective function, the feedback MPC is introduced to obtain better control performance for tracking problem of batch processes. Simulations on a typical batch reactor demonstrate that the satisfactory tracking performance as well as faster convergence speed can be achieved than traditional proportion type （P- t-we） ILC despite the model error and disturbances.展开更多
This paper presents an application of iterative learning control (ILC) technique to the voltage control of solid oxide fuel cell (SOFC) stack. To meet the demands of the control system design, an autoregressive model ...This paper presents an application of iterative learning control (ILC) technique to the voltage control of solid oxide fuel cell (SOFC) stack. To meet the demands of the control system design, an autoregressive model with exogenous input (ARX) is established. Firstly, by regulating the variation of the hydrogen flow rate proportional to that of the current, the fuel utilization of the SOFC is kept within its admissible range. Then, based on the ARX model, three kinds of ILC controllers, i.e. P-, PI- and PD-type are designed to keep the voltage at a desired level. Simulation results demonstrate the potential of the ARX model applied to the control of the SOFC, and prove the excellence of the ILC controllers for the voltage control of the SOFC.展开更多
Battery models are of great importance to develop portable computing systems,for whether the design of low power hardware architecture or the design of battery-aware scheduling policies.In this paper,we present a phys...Battery models are of great importance to develop portable computing systems,for whether the design of low power hardware architecture or the design of battery-aware scheduling policies.In this paper,we present a physically justified iterative computing method to illustrate the discharge,recovery and charge process of Li/Li-ion batteries.The discharge and recovery processes correspond well to an existing accurate analytical battery model:R-V-W's analytical model,and thus interpret this model algorithmically.Our method can also extend R-V-W's model easily to accommodate the charge process.The work will help the system designers to grasp the characteristics of R-V-W's battery model and also,enable to predict the battery behavior in the charge process in a uniform way as the discharge process and the recovery process.Experiments are performed to show the ac-curacy of the extended model by comparing the predicted charge times with those derived from the DUALFOIL simulations.Various profiles with different combinations of battery modes were tested.The experimental results show that the extended battery model preserves high accuracy in predicting the charge behavior.展开更多
In this paper,a reinforced gradient-type iterative learning control pro file is proposed by making use of system matrices and a proper learning step to improve the tracking performance of batch processes disturbed by ...In this paper,a reinforced gradient-type iterative learning control pro file is proposed by making use of system matrices and a proper learning step to improve the tracking performance of batch processes disturbed by external Gaussian white noise.The robustness is analyzed and the range of the step is speci fied by means of statistical technique and matrix theory.Compared with the conventional one,the proposed algorithm is more ef ficient to resist external noise.Numerical simulations of an injection molding process illustrate that the proposed scheme is feasible and effective.展开更多
The key parameters for damage detection and localization are eigenfrequencies, related equivalent viscous damping factors and mode shapes. The classical approach is based on the evaluation of these structural paramete...The key parameters for damage detection and localization are eigenfrequencies, related equivalent viscous damping factors and mode shapes. The classical approach is based on the evaluation of these structural parameters before and after a seismic event, but by using a modern approach based on time-frequency transformations it is possible to quantify these parameters throughout the ground shaking phase. In particular with the use of the S-Transform, it is possible to follow the temporal evolution of the structural dynamics parameters before, during and after an earthquake. In this paper, a methodology for damage localization on framed structures subjected to strong motion earthquakes is proposed based on monitoring the modal curvature variation in the natural frequency of a structure. Two examples of application are described to illustrate the technique: Computer simulation of the nonlinear response of a model, and several laboratory(shaking table) tests performed at the University of Basilicata(Italy). Damage detected using the proposed approach and damage revealed via visual inspections in the tests are compared.展开更多
In this study,a new adaptive morphological filter is developed based on the mathematical morphology algorithm and characteristics of the subtle differences in the waveform morphology in seismic data.The algorithm impr...In this study,a new adaptive morphological filter is developed based on the mathematical morphology algorithm and characteristics of the subtle differences in the waveform morphology in seismic data.The algorithm improves the traditional morphological dilation and corrosion operations.In this study,we propose a multiscale adaptive operator based on the principle of morphological structural“probes”and present the corresponding mathematical proof.Simulation experiments and actual seismic data processing results show that compared with traditional morphological filters,the constructed OCCO-based multistructure adaptive morphological filter can suppress noise to the greatest extent.Moreover,it can effectively improve the SNR of the images,and offers great application prospects.展开更多
With advancements in computing powers and the overall quality of images captured on everyday cameras,a much wider range of possibilities has opened in various scenarios.This fact has several implications for deaf and ...With advancements in computing powers and the overall quality of images captured on everyday cameras,a much wider range of possibilities has opened in various scenarios.This fact has several implications for deaf and dumb people as they have a chance to communicate with a greater number of people much easier.More than ever before,there is a plethora of info about sign language usage in the real world.Sign languages,and by extension the datasets available,are of two forms,isolated sign language and continuous sign language.The main difference between the two types is that in isolated sign language,the hand signs cover individual letters of the alphabet.In continuous sign language,entire words’hand signs are used.This paper will explore a novel deep learning architecture that will use recently published large pre-trained image models to quickly and accurately recognize the alphabets in the American Sign Language(ASL).The study will focus on isolated sign language to demonstrate that it is possible to achieve a high level of classification accuracy on the data,thereby showing that interpreters can be implemented in the real world.The newly proposed Mobile-NetV2 architecture serves as the backbone of this study.It is designed to run on end devices like mobile phones and infer signals(what does it infer)from images in a relatively short amount of time.With the proposed architecture in this paper,the classification accuracy of 98.77%in the Indian Sign Language(ISL)and American Sign Language(ASL)is achieved,outperforming the existing state-of-the-art systems.展开更多
We proposed a method for shape sensing using a few multicore fiber Bragg grating (FBG) sensors ina single-port continuum surgical robot (CSR). The traditional method of utilizing a forward kinematic model tocalculate t...We proposed a method for shape sensing using a few multicore fiber Bragg grating (FBG) sensors ina single-port continuum surgical robot (CSR). The traditional method of utilizing a forward kinematic model tocalculate the shape of a single-port CSR is limited by the accuracy of the model. If FBG sensors are used forshape sensing, their accuracy will be affected by their number, especially in long and flexible CSRs. A fusionmethod based on an extended Kalman filter (EKF) was proposed to solve this problem. Shape reconstructionwas performed using the CSR forward kinematic model and FBG sensors, and the two results were fused usingan EKF. The CSR reconstruction method adopted the incremental form of the forward kinematic model, whilethe FBG sensor method adopted the discrete arc-segment assumption method. The fusion method can eliminatethe inaccuracy of the kinematic model and obtain more accurate shape reconstruction results using only a smallnumber of FBG sensors. We validated our algorithm through experiments on multiple bending shapes underdifferent load conditions. The results show that our method significantly outperformed the traditional methodsin terms of robustness and effectiveness.展开更多
The predominant method for smart phone accessing is confined to methods directing the authentication by means of Point-of-Entry that heavily depend on physiological biometrics like,fingerprint or face.Implicit continuou...The predominant method for smart phone accessing is confined to methods directing the authentication by means of Point-of-Entry that heavily depend on physiological biometrics like,fingerprint or face.Implicit continuous authentication initiating to be loftier to conventional authentication mechanisms by continuously confirming users’identities on continuing basis and mark the instant at which an illegitimate hacker grasps dominance of the session.However,divergent issues remain unaddressed.This research aims to investigate the power of Deep Reinforcement Learning technique to implicit continuous authentication for mobile devices using a method called,Gaussian Weighted Cauchy Kriging-based Continuous Czekanowski’s(GWCK-CC).First,a Gaussian Weighted Non-local Mean Filter Preprocessing model is applied for reducing the noise pre-sent in the raw input face images.Cauchy Kriging Regression function is employed to reduce the dimensionality.Finally,Continuous Czekanowski’s Clas-sification is utilized for proficient classification between the genuine user and attacker.By this way,the proposed GWCK-CC method achieves accurate authen-tication with minimum error rate and time.Experimental assessment of the pro-posed GWCK-CC method and existing methods are carried out with different factors by using UMDAA-02 Face Dataset.The results confirm that the proposed GWCK-CC method enhances authentication accuracy,by 9%,reduces the authen-tication time,and error rate by 44%,and 43%as compared to the existing methods.展开更多
A new form of producing and sharing knowledge has emerged as an international(United States of America,Asia,and Europe) research collaboration,known as the Long-Term Ecological Research(LTER) Network.Although Africa b...A new form of producing and sharing knowledge has emerged as an international(United States of America,Asia,and Europe) research collaboration,known as the Long-Term Ecological Research(LTER) Network.Although Africa boasts rich biodiversity,including endemic species,it lacks the long-term initiatives to underpin sustainable biodiversity managements.At present,climate change may exacerbate hunger and poverty concerns in addition to resulting in ecosystem degradation,land use change,and other threats in Africa.Therefore,ecosystem monitoring was suggested to understanding the effects of climate change and setting strategies to mitigate these changes.This paper aimed to investigate ecosystem monitoring ground sites and address their coverage gaps in Africa to provide a foundation for optimizing the African Ecosystem Research Network(AERN) ground sites.The geographic coordinates and characteristics of ground sites-based ecosystem monitoring were collected from various networks aligned with the LTER implementation in Africa.Additionally,climatic data and biodiversity distribution maps were retrieved from various sources.These data were used to assess the size of existing ground sites and the gaps in description,ecosystems and biomes.The results reveal that there were 1089 sites established by various networks.Among these sites,30.5%,27.5%,and 28.8% had no information of area,year of establishment,current status,respectively.However,68.0% of them had an area equal to or greater than 1 km2.Sites were created progressively over the course of the years,with 68.9% being created from 2000 to 2005.To date,only 41.5% of the sites were operational.The sites were scattered across Africa,but they were concentrated in Eastern and Southern Africa.The unbalanced distribution pattern of the sites left Central and Northern Africa hardly covered,and many unique ecosystems in Central Africa were not included.To sustain these sites,the AERN should be based on operational sites,seeking secure funding by establishing multiple partnerships.展开更多
This paper evaluates the state estimation performance for processing nonlinear/non-Gaussian systems using the cubature particle lter(CPF),which is an estimation algorithm that combines the cubature Kalman lter(CKF)and...This paper evaluates the state estimation performance for processing nonlinear/non-Gaussian systems using the cubature particle lter(CPF),which is an estimation algorithm that combines the cubature Kalman lter(CKF)and the particle lter(PF).The CPF is essentially a realization of PF where the third-degree cubature rule based on numerical integration method is adopted to approximate the proposal distribution.It is benecial where the CKF is used to generate the importance density function in the PF framework for effectively resolving the nonlinear/non-Gaussian problems.Based on the spherical-radial transformation to generate an even number of equally weighted cubature points,the CKF uses cubature points with the same weights through the spherical-radial integration rule and employs an analytical probability density function(pdf)to capture the mean and covariance of the posterior distribution using the total probability theorem and subsequently uses the measurement to update with Bayes’rule.It is capable of acquiring a maximum a posteriori probability estimate of the nonlinear system,and thus the importance density function can be used to approximate the true posterior density distribution.In Bayesian ltering,the nonlinear lter performs well when all conditional densities are assumed Gaussian.When applied to the nonlinear/non-Gaussian distribution systems,the CPF algorithm can remarkably improve the estimation accuracy as compared to the other particle lterbased approaches,such as the extended particle lter(EPF),and unscented particle lter(UPF),and also the Kalman lter(KF)-type approaches,such as the extended Kalman lter(EKF),unscented Kalman lter(UKF)and CKF.Two illustrative examples are presented showing that the CPF achieves better performance as compared to the other approaches.展开更多
Pest detection in agricultural cropfields is the most challenging task,so an effective pest detection technique is required to detect insects automatically.Image processing techniques are widely preferred in agricultur...Pest detection in agricultural cropfields is the most challenging task,so an effective pest detection technique is required to detect insects automatically.Image processing techniques are widely preferred in agricultural science because they offer multiple advantages like maximal crop protection,improved crop man-agement and productivity.On the other hand,developing the automatic pest mon-itoring system dramatically reduces the workforce and errors.Existing image processing approaches are limited due to the disadvantages like poor efficiency and less accuracy.Therefore,a successful image processing technique based on FF-GWO-CNN classification algorithm is introduced for effective pest monitor-ing and detection.The four-step image processing technique begins with image pre-processing,removing the insect image’s noise and sunlight illumination by utilizing an adaptive medianfilter.The insects’size and shape are identified using the Expectation Maximization Algorithm(EMA)based clustering technique,which involves not only clustering the data but also uncovering the correlations by visualizing the global shape of an image.Speeded up robust feature(SURF)method is employed to select the best possible image features.Eventually,the image with best features is classified by introducing a hybrid FF-GWO-CNN algorithm,which combines the benefits of Firefly(FF),Grey Wolf Optimization(GWO)and Convolutional Neural Network(CNN)classification algorithm for enhancing the classification accuracy.The entire work is executed in MATLAB simulation software.The test result reveals that the suggested technique has deliv-ered optimal performance with high accuracy of 97.5%,precision of 94%,recall of 92%and F-score value of 92%.展开更多
In spite of the advancement in computerized imaging,many image modalities produce images with commotion influencing both the visual quality and upsetting quantitative image analysis.In this way,the research in the zone...In spite of the advancement in computerized imaging,many image modalities produce images with commotion influencing both the visual quality and upsetting quantitative image analysis.In this way,the research in the zone of image denoising is very dynamic.Among an extraordinary assortment of image restoration and denoising techniques the neural network system-based noise sup-pression is a basic and productive methodology.In this paper,Bilateral Filter(BF)based Modular Neural Networks(MNN)has been utilized for speckle noise sup-pression in the ultrasound image.Initial step the BFfilter is used tofilter the input image.From the output of BF,statistical features such as mean,standard devia-tion,median and kurtosis have been extracted and these features are used to train the MNN.Then,thefiltered images from the BF are again denoised using MNN.The ultrasound dataset from the Kaggle site is used for the training and testing process.The simulation outcomes demonstrate that the BF-MNNfiltering method performs better for the multiplicative noise concealment in UltraSound(US)images.From the simulation results,it has been observed that BF-MNN performs better than the existing techniques in terms of peak signal to noise ratio(34.89),Structural Similarity Index(0.89)and Edge Preservation Index(0.67).展开更多
Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images fro...Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images from the database.This CBIR system helps a physician to give better treatment.Local features must be described with the input images to retrieve similar images.Exist-ing methods are inefficient and inaccurate by failing in local features analysis.Hence,efficient digital mammography image retrieval needs to be implemented.This paper proposed reliable recovery of the mammographic image from the data-base,which requires the removal of noise using Kalmanfilter and scale-invariant feature transform(SIFT)for feature extraction with Crow Search Optimization-based the deep belief network(CSO-DBN).This proposed technique decreases the complexity,cost,energy,and time consumption.Training the proposed model using a deep belief network and validation is performed.Finally,the testing pro-cess gives better performance compared to existing techniques.The accuracy rate of the proposed work CSO-DBN is 0.9344,whereas the support vector machine(SVM)(0.5434),naïve Bayes(NB)(0.7014),Butterfly Optimization Algorithm(BOA)(0.8156),and Cat Swarm Optimization(CSO)(0.8852).展开更多
In medical science for envisaging human body’s phenomenal structure a major part has been driven by image processing techniques.Major objective of this work is to detect of cerebral atherosclerosis for image segmenta...In medical science for envisaging human body’s phenomenal structure a major part has been driven by image processing techniques.Major objective of this work is to detect of cerebral atherosclerosis for image segmentation applica-tion.Detection of some abnormal structures in human body has become a difficult task to complete with some simple images.For expounding and distinguishing neural architecture of human brain in an effective manner,MRI(Magnetic Reso-nance Imaging)is one of the most suitable and significant technique.Here we work on detection of Cerebral Atherosclerosis from MRI images of patients.Cer-ebral Atherosclerosis is a cerebral vascular disease causes narrowing of the arteries due to buildup of fatty plaque inside the blood vessels of the brain.It leads to Ischemic stroke if not diagnosed early.Stroke affects majorly old age people and percentage of affected women is more compared to men.Results:Preproces-sing is done by using alpha trimmed meanfilter which is used to remove noise and also it enhances the image.Segmentation of cerebral atherosclerosis is done by using K-means clustering,Contextual clustering,and proposed Hybrid algo-rithm.Various parameters like Correlation,Pixel density,energy is determined and from the analysis of parameters it is determined that proposed Hybrid algo-rithm is efficient.展开更多
基金Supported in part by the State Key Development Program for Basic Research of China(2012CB720505)the National Natural Science Foundation of China(61174105,60874049)
文摘Based on the two-dimensional （2D） system theory, an integrated predictive iterative learning control （2D-IPILC） strategy for batch processes is presented. First, the output response and the error transition model predictions along the batch index can be calculated analytically due to the 2D Roesser model of the batch process. Then, an integrated framework of combining iterative learning control （ILC） and model predictive control （MPC） is formed reasonably. The output of feedforward ILC is estimated on the basis of the predefined process 2D model. By min- imizing a quadratic objective function, the feedback MPC is introduced to obtain better control performance for tracking problem of batch processes. Simulations on a typical batch reactor demonstrate that the satisfactory tracking performance as well as faster convergence speed can be achieved than traditional proportion type （P- t-we） ILC despite the model error and disturbances.
基金Project (No. 2006AA05Z148) supported by the Hi-Tech Research and Development Program (863) of China
文摘This paper presents an application of iterative learning control (ILC) technique to the voltage control of solid oxide fuel cell (SOFC) stack. To meet the demands of the control system design, an autoregressive model with exogenous input (ARX) is established. Firstly, by regulating the variation of the hydrogen flow rate proportional to that of the current, the fuel utilization of the SOFC is kept within its admissible range. Then, based on the ARX model, three kinds of ILC controllers, i.e. P-, PI- and PD-type are designed to keep the voltage at a desired level. Simulation results demonstrate the potential of the ARX model applied to the control of the SOFC, and prove the excellence of the ILC controllers for the voltage control of the SOFC.
基金Project partly supported by the Key Program of the National NaturalScience Foundation of China (No. 60533040)the National Natural Science Funds for Distinguished Young Scholar (No. 60525202)+1 种基金the Program for New Century Excellent Talents in University (No. NCET-04-0545)the Key Scientific and Technological Project of Hangzhou Technology Bureau (No. 20062412B01),China
文摘Battery models are of great importance to develop portable computing systems,for whether the design of low power hardware architecture or the design of battery-aware scheduling policies.In this paper,we present a physically justified iterative computing method to illustrate the discharge,recovery and charge process of Li/Li-ion batteries.The discharge and recovery processes correspond well to an existing accurate analytical battery model:R-V-W's analytical model,and thus interpret this model algorithmically.Our method can also extend R-V-W's model easily to accommodate the charge process.The work will help the system designers to grasp the characteristics of R-V-W's battery model and also,enable to predict the battery behavior in the charge process in a uniform way as the discharge process and the recovery process.Experiments are performed to show the ac-curacy of the extended model by comparing the predicted charge times with those derived from the DUALFOIL simulations.Various profiles with different combinations of battery modes were tested.The experimental results show that the extended battery model preserves high accuracy in predicting the charge behavior.
基金Supported by National Natural Science Foundation of China(F010114-6097414061273135)
文摘In this paper,a reinforced gradient-type iterative learning control pro file is proposed by making use of system matrices and a proper learning step to improve the tracking performance of batch processes disturbed by external Gaussian white noise.The robustness is analyzed and the range of the step is speci fied by means of statistical technique and matrix theory.Compared with the conventional one,the proposed algorithm is more ef ficient to resist external noise.Numerical simulations of an injection molding process illustrate that the proposed scheme is feasible and effective.
基金Italian Civil Protection within the Projects DPC-RELUIS 2010-2013(Task 3.1)DPC-RELUIS 2014(Special Project"Monitoraggio")
文摘The key parameters for damage detection and localization are eigenfrequencies, related equivalent viscous damping factors and mode shapes. The classical approach is based on the evaluation of these structural parameters before and after a seismic event, but by using a modern approach based on time-frequency transformations it is possible to quantify these parameters throughout the ground shaking phase. In particular with the use of the S-Transform, it is possible to follow the temporal evolution of the structural dynamics parameters before, during and after an earthquake. In this paper, a methodology for damage localization on framed structures subjected to strong motion earthquakes is proposed based on monitoring the modal curvature variation in the natural frequency of a structure. Two examples of application are described to illustrate the technique: Computer simulation of the nonlinear response of a model, and several laboratory(shaking table) tests performed at the University of Basilicata(Italy). Damage detected using the proposed approach and damage revealed via visual inspections in the tests are compared.
基金This work was supported National Key R&D Program of China(2017YFC0601505).
文摘In this study,a new adaptive morphological filter is developed based on the mathematical morphology algorithm and characteristics of the subtle differences in the waveform morphology in seismic data.The algorithm improves the traditional morphological dilation and corrosion operations.In this study,we propose a multiscale adaptive operator based on the principle of morphological structural“probes”and present the corresponding mathematical proof.Simulation experiments and actual seismic data processing results show that compared with traditional morphological filters,the constructed OCCO-based multistructure adaptive morphological filter can suppress noise to the greatest extent.Moreover,it can effectively improve the SNR of the images,and offers great application prospects.
文摘With advancements in computing powers and the overall quality of images captured on everyday cameras,a much wider range of possibilities has opened in various scenarios.This fact has several implications for deaf and dumb people as they have a chance to communicate with a greater number of people much easier.More than ever before,there is a plethora of info about sign language usage in the real world.Sign languages,and by extension the datasets available,are of two forms,isolated sign language and continuous sign language.The main difference between the two types is that in isolated sign language,the hand signs cover individual letters of the alphabet.In continuous sign language,entire words’hand signs are used.This paper will explore a novel deep learning architecture that will use recently published large pre-trained image models to quickly and accurately recognize the alphabets in the American Sign Language(ASL).The study will focus on isolated sign language to demonstrate that it is possible to achieve a high level of classification accuracy on the data,thereby showing that interpreters can be implemented in the real world.The newly proposed Mobile-NetV2 architecture serves as the backbone of this study.It is designed to run on end devices like mobile phones and infer signals(what does it infer)from images in a relatively short amount of time.With the proposed architecture in this paper,the classification accuracy of 98.77%in the Indian Sign Language(ISL)and American Sign Language(ASL)is achieved,outperforming the existing state-of-the-art systems.
基金the National Natural Science Foundation of China(Nos.61873257 and U20A20195)the Project of Natural Science Foundation of Liaoning Province(No.2021-MS-033)the Foundation of Millions of Talents Project of the Department of Human Resources and Social Security of Liaoning Province(No.2021921037)。
文摘We proposed a method for shape sensing using a few multicore fiber Bragg grating (FBG) sensors ina single-port continuum surgical robot (CSR). The traditional method of utilizing a forward kinematic model tocalculate the shape of a single-port CSR is limited by the accuracy of the model. If FBG sensors are used forshape sensing, their accuracy will be affected by their number, especially in long and flexible CSRs. A fusionmethod based on an extended Kalman filter (EKF) was proposed to solve this problem. Shape reconstructionwas performed using the CSR forward kinematic model and FBG sensors, and the two results were fused usingan EKF. The CSR reconstruction method adopted the incremental form of the forward kinematic model, whilethe FBG sensor method adopted the discrete arc-segment assumption method. The fusion method can eliminatethe inaccuracy of the kinematic model and obtain more accurate shape reconstruction results using only a smallnumber of FBG sensors. We validated our algorithm through experiments on multiple bending shapes underdifferent load conditions. The results show that our method significantly outperformed the traditional methodsin terms of robustness and effectiveness.
文摘The predominant method for smart phone accessing is confined to methods directing the authentication by means of Point-of-Entry that heavily depend on physiological biometrics like,fingerprint or face.Implicit continuous authentication initiating to be loftier to conventional authentication mechanisms by continuously confirming users’identities on continuing basis and mark the instant at which an illegitimate hacker grasps dominance of the session.However,divergent issues remain unaddressed.This research aims to investigate the power of Deep Reinforcement Learning technique to implicit continuous authentication for mobile devices using a method called,Gaussian Weighted Cauchy Kriging-based Continuous Czekanowski’s(GWCK-CC).First,a Gaussian Weighted Non-local Mean Filter Preprocessing model is applied for reducing the noise pre-sent in the raw input face images.Cauchy Kriging Regression function is employed to reduce the dimensionality.Finally,Continuous Czekanowski’s Clas-sification is utilized for proficient classification between the genuine user and attacker.By this way,the proposed GWCK-CC method achieves accurate authen-tication with minimum error rate and time.Experimental assessment of the pro-posed GWCK-CC method and existing methods are carried out with different factors by using UMDAA-02 Face Dataset.The results confirm that the proposed GWCK-CC method enhances authentication accuracy,by 9%,reduces the authen-tication time,and error rate by 44%,and 43%as compared to the existing methods.
基金Under the auspices of National Natural Science Foundation of China(No.31161140355)
文摘A new form of producing and sharing knowledge has emerged as an international(United States of America,Asia,and Europe) research collaboration,known as the Long-Term Ecological Research(LTER) Network.Although Africa boasts rich biodiversity,including endemic species,it lacks the long-term initiatives to underpin sustainable biodiversity managements.At present,climate change may exacerbate hunger and poverty concerns in addition to resulting in ecosystem degradation,land use change,and other threats in Africa.Therefore,ecosystem monitoring was suggested to understanding the effects of climate change and setting strategies to mitigate these changes.This paper aimed to investigate ecosystem monitoring ground sites and address their coverage gaps in Africa to provide a foundation for optimizing the African Ecosystem Research Network(AERN) ground sites.The geographic coordinates and characteristics of ground sites-based ecosystem monitoring were collected from various networks aligned with the LTER implementation in Africa.Additionally,climatic data and biodiversity distribution maps were retrieved from various sources.These data were used to assess the size of existing ground sites and the gaps in description,ecosystems and biomes.The results reveal that there were 1089 sites established by various networks.Among these sites,30.5%,27.5%,and 28.8% had no information of area,year of establishment,current status,respectively.However,68.0% of them had an area equal to or greater than 1 km2.Sites were created progressively over the course of the years,with 68.9% being created from 2000 to 2005.To date,only 41.5% of the sites were operational.The sites were scattered across Africa,but they were concentrated in Eastern and Southern Africa.The unbalanced distribution pattern of the sites left Central and Northern Africa hardly covered,and many unique ecosystems in Central Africa were not included.To sustain these sites,the AERN should be based on operational sites,seeking secure funding by establishing multiple partnerships.
基金supported by the Ministry of Science and Technology,Taiwan[Grant No.MOST 108-2221-E-019-013]。
文摘This paper evaluates the state estimation performance for processing nonlinear/non-Gaussian systems using the cubature particle lter(CPF),which is an estimation algorithm that combines the cubature Kalman lter(CKF)and the particle lter(PF).The CPF is essentially a realization of PF where the third-degree cubature rule based on numerical integration method is adopted to approximate the proposal distribution.It is benecial where the CKF is used to generate the importance density function in the PF framework for effectively resolving the nonlinear/non-Gaussian problems.Based on the spherical-radial transformation to generate an even number of equally weighted cubature points,the CKF uses cubature points with the same weights through the spherical-radial integration rule and employs an analytical probability density function(pdf)to capture the mean and covariance of the posterior distribution using the total probability theorem and subsequently uses the measurement to update with Bayes’rule.It is capable of acquiring a maximum a posteriori probability estimate of the nonlinear system,and thus the importance density function can be used to approximate the true posterior density distribution.In Bayesian ltering,the nonlinear lter performs well when all conditional densities are assumed Gaussian.When applied to the nonlinear/non-Gaussian distribution systems,the CPF algorithm can remarkably improve the estimation accuracy as compared to the other particle lterbased approaches,such as the extended particle lter(EPF),and unscented particle lter(UPF),and also the Kalman lter(KF)-type approaches,such as the extended Kalman lter(EKF),unscented Kalman lter(UKF)and CKF.Two illustrative examples are presented showing that the CPF achieves better performance as compared to the other approaches.
基金supported by“Catalyzed and supported by Tamilnadu State Council for Science and Technology,Dept.of Higher Education,Government of Tamilnadu.”。
文摘Pest detection in agricultural cropfields is the most challenging task,so an effective pest detection technique is required to detect insects automatically.Image processing techniques are widely preferred in agricultural science because they offer multiple advantages like maximal crop protection,improved crop man-agement and productivity.On the other hand,developing the automatic pest mon-itoring system dramatically reduces the workforce and errors.Existing image processing approaches are limited due to the disadvantages like poor efficiency and less accuracy.Therefore,a successful image processing technique based on FF-GWO-CNN classification algorithm is introduced for effective pest monitor-ing and detection.The four-step image processing technique begins with image pre-processing,removing the insect image’s noise and sunlight illumination by utilizing an adaptive medianfilter.The insects’size and shape are identified using the Expectation Maximization Algorithm(EMA)based clustering technique,which involves not only clustering the data but also uncovering the correlations by visualizing the global shape of an image.Speeded up robust feature(SURF)method is employed to select the best possible image features.Eventually,the image with best features is classified by introducing a hybrid FF-GWO-CNN algorithm,which combines the benefits of Firefly(FF),Grey Wolf Optimization(GWO)and Convolutional Neural Network(CNN)classification algorithm for enhancing the classification accuracy.The entire work is executed in MATLAB simulation software.The test result reveals that the suggested technique has deliv-ered optimal performance with high accuracy of 97.5%,precision of 94%,recall of 92%and F-score value of 92%.
文摘In spite of the advancement in computerized imaging,many image modalities produce images with commotion influencing both the visual quality and upsetting quantitative image analysis.In this way,the research in the zone of image denoising is very dynamic.Among an extraordinary assortment of image restoration and denoising techniques the neural network system-based noise sup-pression is a basic and productive methodology.In this paper,Bilateral Filter(BF)based Modular Neural Networks(MNN)has been utilized for speckle noise sup-pression in the ultrasound image.Initial step the BFfilter is used tofilter the input image.From the output of BF,statistical features such as mean,standard devia-tion,median and kurtosis have been extracted and these features are used to train the MNN.Then,thefiltered images from the BF are again denoised using MNN.The ultrasound dataset from the Kaggle site is used for the training and testing process.The simulation outcomes demonstrate that the BF-MNNfiltering method performs better for the multiplicative noise concealment in UltraSound(US)images.From the simulation results,it has been observed that BF-MNN performs better than the existing techniques in terms of peak signal to noise ratio(34.89),Structural Similarity Index(0.89)and Edge Preservation Index(0.67).
文摘Mammography is considered a significant image for accurate breast cancer detection.Content-based image retrieval(CBIR)contributes to classifying the query mammography image and retrieves similar mammographic images from the database.This CBIR system helps a physician to give better treatment.Local features must be described with the input images to retrieve similar images.Exist-ing methods are inefficient and inaccurate by failing in local features analysis.Hence,efficient digital mammography image retrieval needs to be implemented.This paper proposed reliable recovery of the mammographic image from the data-base,which requires the removal of noise using Kalmanfilter and scale-invariant feature transform(SIFT)for feature extraction with Crow Search Optimization-based the deep belief network(CSO-DBN).This proposed technique decreases the complexity,cost,energy,and time consumption.Training the proposed model using a deep belief network and validation is performed.Finally,the testing pro-cess gives better performance compared to existing techniques.The accuracy rate of the proposed work CSO-DBN is 0.9344,whereas the support vector machine(SVM)(0.5434),naïve Bayes(NB)(0.7014),Butterfly Optimization Algorithm(BOA)(0.8156),and Cat Swarm Optimization(CSO)(0.8852).
文摘In medical science for envisaging human body’s phenomenal structure a major part has been driven by image processing techniques.Major objective of this work is to detect of cerebral atherosclerosis for image segmentation applica-tion.Detection of some abnormal structures in human body has become a difficult task to complete with some simple images.For expounding and distinguishing neural architecture of human brain in an effective manner,MRI(Magnetic Reso-nance Imaging)is one of the most suitable and significant technique.Here we work on detection of Cerebral Atherosclerosis from MRI images of patients.Cer-ebral Atherosclerosis is a cerebral vascular disease causes narrowing of the arteries due to buildup of fatty plaque inside the blood vessels of the brain.It leads to Ischemic stroke if not diagnosed early.Stroke affects majorly old age people and percentage of affected women is more compared to men.Results:Preproces-sing is done by using alpha trimmed meanfilter which is used to remove noise and also it enhances the image.Segmentation of cerebral atherosclerosis is done by using K-means clustering,Contextual clustering,and proposed Hybrid algo-rithm.Various parameters like Correlation,Pixel density,energy is determined and from the analysis of parameters it is determined that proposed Hybrid algo-rithm is efficient.
