Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes over...Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more complex.The existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s performance.We analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream classification.Precision, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority classes.The study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.展开更多
Long Range Wide Area Network (LoRaWAN) in the Internet ofThings (IoT) domain has been the subject of interest for researchers. Thereis an increasing demand to localize these IoT devices using LoRaWAN dueto the quickly...Long Range Wide Area Network (LoRaWAN) in the Internet ofThings (IoT) domain has been the subject of interest for researchers. Thereis an increasing demand to localize these IoT devices using LoRaWAN dueto the quickly growing number of IoT devices. LoRaWAN is well suited tosupport localization applications in IoTs due to its low power consumptionand long range. Multiple approaches have been proposed to solve the localizationproblem using LoRaWAN. The Expected Signal Power (ESP) basedtrilateration algorithm has the significant potential for localization becauseESP can identify the signal’s energy below the noise floor with no additionalhardware requirements and ease of implementation. This research articleoffers the technical evaluation of the trilateration technique, its efficiency,and its limitations for the localization using LoRa ESP in a large outdoorpopulated campus environment. Additionally, experimental evaluations areconducted to determine the effects of frequency hopping, outlier removal, andincreasing the number of gateways on localization accuracy. Results obtainedfrom the experiment show the importance of calculating the path loss exponentfor every frequency to circumvent the high localization error because ofthe frequency hopping, thus improving the localization performance withoutthe need of using only a single frequency.展开更多
One of the most pressing concerns for the consumer market is the detection of adulteration in meat products due to their preciousness.The rapid and accurate identification mechanism for lard adulteration in meat produ...One of the most pressing concerns for the consumer market is the detection of adulteration in meat products due to their preciousness.The rapid and accurate identification mechanism for lard adulteration in meat products is highly necessary,for developing a mechanism trusted by consumers and that can be used to make a definitive diagnosis.Fourier Transform Infrared Spectroscopy(FTIR)is used in this work to identify lard adulteration in cow,lamb,and chicken samples.A simplified extraction method was implied to obtain the lipids from pure and adulterated meat.Adulterated samples were obtained by mixing lard with chicken,lamb,and beef with different concentrations(10%–50%v/v).Principal component analysis(PCA)and partial least square(PLS)were used to develop a calibration model at 800–3500 cm^(−1).Three-dimension PCA was successfully used by dividing the spectrum in three regions to classify lard meat adulteration in chicken,lamb,and beef samples.The corresponding FTIR peaks for the lard have been observed at 1159.6,1743.4,2853.1,and 2922.5 cm−1,which differentiate chicken,lamb,and beef samples.The wavenumbers offer the highest determination coefficient R2 value of 0.846 and lowest root mean square error of calibration(RMSEC)and root mean square error prediction(RMSEP)with an accuracy of 84.6%.Even the tiniest fat adulteration up to 10%can be reliably discovered using this methodology.展开更多
Renewable energy is essential for planet sustainability.Renewable energy output forecasting has a significant impact on making decisions related to operating and managing power systems.Accurate prediction of renewable...Renewable energy is essential for planet sustainability.Renewable energy output forecasting has a significant impact on making decisions related to operating and managing power systems.Accurate prediction of renewable energy output is vital to ensure grid reliability and permanency and reduce the risk and cost of the energy market and systems.Deep learning’s recent success in many applications has attracted researchers to this field and its promising potential is manifested in the richness of the proposed methods and the increasing number of publications.To facilitate further research and development in this area,this paper provides a review of deep learning-based solar and wind energy forecasting research published during the last five years discussing extensively the data and datasets used in the reviewed works,the data pre-processing methods,deterministic and probabilistic methods,and evaluation and comparison methods.The core characteristics of all the reviewed works are summarised in tabular forms to enable methodological comparisons.The current challenges in the field and future research directions are given.The trends show that hybrid forecasting models are the most used in this field followed by Recurrent Neural Network models including Long Short-Term Memory and Gated Recurrent Unit,and in the third place Convolutional Neural Networks.We also find that probabilistic and multistep ahead forecasting methods are gaining more attention.Moreover,we devise a broad taxonomy of the research using the key insights gained from this extensive review,the taxonomy we believe will be vital in understanding the cutting-edge and accelerating innovation in this field.展开更多
Feynman’s path integral reformulates the quantum Schrödinger differential equation to be an integral equation.It has been being widely used to compute internuclear quantum-statistical effects on many-body molecu...Feynman’s path integral reformulates the quantum Schrödinger differential equation to be an integral equation.It has been being widely used to compute internuclear quantum-statistical effects on many-body molecular systems.In this Review,the molecular Schrödinger equation will first be introduced,together with the BornOppenheimer approximation that decouples electronic and internuclear motions.Some effective semiclassical potentials,e.g.,centroid potential,which are all formulated in terms of Feynman’s path integral,will be discussed and compared.These semiclassical potentials can be used to directly calculate the quantum canonical partition function without individual Schrödinger’s energy eigenvalues.As a result,path integrations are conventionally performed with Monte Carlo and molecular dynamics sampling techniques.To complement these techniques,we will examine how Kleinert’s variational perturbation(KP)theory can provide a complete theoretical foundation for developing non-sampling/non-stochastic methods to systematically calculate centroid potential.To enable the powerful KP theory to be practical for many-body molecular systems,we have proposed a new path-integral method:automated integrationfree path-integral(AIF-PI)method.Due to the integration-free and computationally inexpensive characteristics of our AIF-PI method,we have used it to perform ab initio path-integral calculations of kinetic isotope effects on proton-transfer and RNA-related phosphoryl-transfer chemical reactions.The computational procedure of using our AIF-PI method,along with the features of our new centroid path-integral theory at the minimum of the absolute-zero energy(AMAZE),are also highlighted in this review.展开更多
We present a parallel and linear scaling implementation of the calculation of the electrostatic potential arising from an arbitrary charge distribution.Our approach is making use of the multi-resolution basis of multi...We present a parallel and linear scaling implementation of the calculation of the electrostatic potential arising from an arbitrary charge distribution.Our approach is making use of the multi-resolution basis of multiwavelets.The potential is obtained as the direct solution of the Poisson equation in its Green’s function integral form.In the multiwavelet basis,the formally non local integral operator decays rapidly to negligible values away from the main diagonal,yielding an effectively banded structure where the bandwidth is only dictated by the requested accuracy.This sparse operator structure has been exploited to achieve linear scaling and parallel algorithms.Parallelization has been achieved both through the shared memory(OpenMP)and the message passing interface(MPI)paradigm.Our implementation has been tested by computing the electrostatic potential of the electronic density of long-chain alkanes and diamond fragments showing(sub)linear scaling with the system size and efficent parallelization.展开更多
基金The authors would like to extend their gratitude to Universiti Teknologi PETRONAS (Malaysia)for funding this research through grant number (015LA0-037).
文摘Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more complex.The existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s performance.We analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream classification.Precision, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority classes.The study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.
基金the ADEK Award for Research Excellence (AARE19-245)2019.
文摘Long Range Wide Area Network (LoRaWAN) in the Internet ofThings (IoT) domain has been the subject of interest for researchers. Thereis an increasing demand to localize these IoT devices using LoRaWAN dueto the quickly growing number of IoT devices. LoRaWAN is well suited tosupport localization applications in IoTs due to its low power consumptionand long range. Multiple approaches have been proposed to solve the localizationproblem using LoRaWAN. The Expected Signal Power (ESP) basedtrilateration algorithm has the significant potential for localization becauseESP can identify the signal’s energy below the noise floor with no additionalhardware requirements and ease of implementation. This research articleoffers the technical evaluation of the trilateration technique, its efficiency,and its limitations for the localization using LoRa ESP in a large outdoorpopulated campus environment. Additionally, experimental evaluations areconducted to determine the effects of frequency hopping, outlier removal, andincreasing the number of gateways on localization accuracy. Results obtainedfrom the experiment show the importance of calculating the path loss exponentfor every frequency to circumvent the high localization error because ofthe frequency hopping, thus improving the localization performance withoutthe need of using only a single frequency.
文摘One of the most pressing concerns for the consumer market is the detection of adulteration in meat products due to their preciousness.The rapid and accurate identification mechanism for lard adulteration in meat products is highly necessary,for developing a mechanism trusted by consumers and that can be used to make a definitive diagnosis.Fourier Transform Infrared Spectroscopy(FTIR)is used in this work to identify lard adulteration in cow,lamb,and chicken samples.A simplified extraction method was implied to obtain the lipids from pure and adulterated meat.Adulterated samples were obtained by mixing lard with chicken,lamb,and beef with different concentrations(10%–50%v/v).Principal component analysis(PCA)and partial least square(PLS)were used to develop a calibration model at 800–3500 cm^(−1).Three-dimension PCA was successfully used by dividing the spectrum in three regions to classify lard meat adulteration in chicken,lamb,and beef samples.The corresponding FTIR peaks for the lard have been observed at 1159.6,1743.4,2853.1,and 2922.5 cm−1,which differentiate chicken,lamb,and beef samples.The wavenumbers offer the highest determination coefficient R2 value of 0.846 and lowest root mean square error of calibration(RMSEC)and root mean square error prediction(RMSEP)with an accuracy of 84.6%.Even the tiniest fat adulteration up to 10%can be reliably discovered using this methodology.
文摘Renewable energy is essential for planet sustainability.Renewable energy output forecasting has a significant impact on making decisions related to operating and managing power systems.Accurate prediction of renewable energy output is vital to ensure grid reliability and permanency and reduce the risk and cost of the energy market and systems.Deep learning’s recent success in many applications has attracted researchers to this field and its promising potential is manifested in the richness of the proposed methods and the increasing number of publications.To facilitate further research and development in this area,this paper provides a review of deep learning-based solar and wind energy forecasting research published during the last five years discussing extensively the data and datasets used in the reviewed works,the data pre-processing methods,deterministic and probabilistic methods,and evaluation and comparison methods.The core characteristics of all the reviewed works are summarised in tabular forms to enable methodological comparisons.The current challenges in the field and future research directions are given.The trends show that hybrid forecasting models are the most used in this field followed by Recurrent Neural Network models including Long Short-Term Memory and Gated Recurrent Unit,and in the third place Convolutional Neural Networks.We also find that probabilistic and multistep ahead forecasting methods are gaining more attention.Moreover,we devise a broad taxonomy of the research using the key insights gained from this extensive review,the taxonomy we believe will be vital in understanding the cutting-edge and accelerating innovation in this field.
基金supported by HK RGC(ECS-209813)NSF of China(NSFC-21303151)+2 种基金HKBU FRG(FRG2/12-13/037)startup funds(38-40-088 and 40-49-495)to K.-Y.WongThe computing resources for our work summarized in this Review were supported in part by Minnesota Supercomputing Institute,and High Performance Cluster Computing Centre and Office of Information Technology at HKBU(sciblade&jiraiya).
文摘Feynman’s path integral reformulates the quantum Schrödinger differential equation to be an integral equation.It has been being widely used to compute internuclear quantum-statistical effects on many-body molecular systems.In this Review,the molecular Schrödinger equation will first be introduced,together with the BornOppenheimer approximation that decouples electronic and internuclear motions.Some effective semiclassical potentials,e.g.,centroid potential,which are all formulated in terms of Feynman’s path integral,will be discussed and compared.These semiclassical potentials can be used to directly calculate the quantum canonical partition function without individual Schrödinger’s energy eigenvalues.As a result,path integrations are conventionally performed with Monte Carlo and molecular dynamics sampling techniques.To complement these techniques,we will examine how Kleinert’s variational perturbation(KP)theory can provide a complete theoretical foundation for developing non-sampling/non-stochastic methods to systematically calculate centroid potential.To enable the powerful KP theory to be practical for many-body molecular systems,we have proposed a new path-integral method:automated integrationfree path-integral(AIF-PI)method.Due to the integration-free and computationally inexpensive characteristics of our AIF-PI method,we have used it to perform ab initio path-integral calculations of kinetic isotope effects on proton-transfer and RNA-related phosphoryl-transfer chemical reactions.The computational procedure of using our AIF-PI method,along with the features of our new centroid path-integral theory at the minimum of the absolute-zero energy(AMAZE),are also highlighted in this review.
基金supported by the Research Council of Norway through a Cen-tre of Excellence Grant(Grant No.179568/V30)from the Norwegian Super-computing Program(NOTUR)through a grant of computer time(Grant No.NN4654K).
文摘We present a parallel and linear scaling implementation of the calculation of the electrostatic potential arising from an arbitrary charge distribution.Our approach is making use of the multi-resolution basis of multiwavelets.The potential is obtained as the direct solution of the Poisson equation in its Green’s function integral form.In the multiwavelet basis,the formally non local integral operator decays rapidly to negligible values away from the main diagonal,yielding an effectively banded structure where the bandwidth is only dictated by the requested accuracy.This sparse operator structure has been exploited to achieve linear scaling and parallel algorithms.Parallelization has been achieved both through the shared memory(OpenMP)and the message passing interface(MPI)paradigm.Our implementation has been tested by computing the electrostatic potential of the electronic density of long-chain alkanes and diamond fragments showing(sub)linear scaling with the system size and efficent parallelization.
