Molecular chains of elastomer networks are modeled as ideal, finite, Freely Jointed Chains (FJC). We first develop a compact, closed-form, mathematically accurate representation of this model. We begin with the closed...
详细信息
Linear Induction motors are becoming more and more popular day by day. High speed Electromagnetic propulsion is the demand of many upcoming industry projects viz. the Hyper-loop transport system, factory operation and...
详细信息
Linear Induction motors are becoming more and more popular day by day. High speed Electromagnetic propulsion is the demand of many upcoming industry projects viz. the Hyper-loop transport system, factory operation and Defence establishment for moving large mass rapidly. The short secondary long primary Double Sided Linear Induction Motor (DSLIM), with conventional single layer or double layer distributed winding when operating at extremely high acceleration results in oscillating thrust which restricts the movement of the mover. A case study has been reported for wayside Hyper-loop system with German Silver mover gives satisfactory performance for moving a heavy mass at high speed using DSLIM. Here slot by slot double layer three phase winding has been used.
As deep learning models become more prevalent in smart grid systems, ensuring their accuracy in tasks like identifying abnormal customer behavior is increasingly important. As its use is increased in smart grids to de...
详细信息
ISBN:
(数字)9798331539948
ISBN:
(纸本)9798331539955
As deep learning models become more prevalent in smart grid systems, ensuring their accuracy in tasks like identifying abnormal customer behavior is increasingly important. As its use is increased in smart grids to detect energy theft, crafting adversarial data by attackers to deceive the model to get the desired output is also increased. Evasion attacks (EA) attempt to evade detection by misclassifying input data during testing. The manipulation of data inputs is done so that it is not noticeable to humans but can cause the machine learning (ML) model to produce incorrect results. Electricity theft has become a major problem for utility companies that need to be dealt with effectively. Convolutional Neural Network (CNN) and AdaBoost hybrid model have been developed that promise to detect electricity theft with high accuracy. However, this model is also vulnerable to evasion attacks that can render it ineffective. In this paper, to make the detection system more robust, we present an algorithm to create adversarial data for evasion attacks against a hybrid model combining Convolutional Neural Network and Adaboost (CNN-Adaboost). Generated adversarial data from the proposed algorithm is crafted on the model to test its performance. Our proposed attack is validated with State Grid Corporation of China (SGCC) dataset. We test the CNN-Adaboost energy theft detection model and other models’ performance under 5% and 10% evasion attacks. Our findings reveal model performance degradation under our proposed generative evasion attack ranging from 96.35% to ${8 9. 2 3 \%}$. These adversaries are useful for designing robust and secure ML models. The proposed attack can be utilized to test energy theft detection (ETD) models in industrial and commercial settings.
The ornamental and commercial values of herbaceous peony(Paeonia lactiflora Pall.)are directly related to its flower ***,the molecular mechanisms underlying the type formation of *** flowers have not been studied in g...
详细信息
The ornamental and commercial values of herbaceous peony(Paeonia lactiflora Pall.)are directly related to its flower ***,the molecular mechanisms underlying the type formation of *** flowers have not been studied in great *** studies identified,using integrated multipleomics analysis,revealed that APETALA2(AP2)is an important candidate gene that modulates type formation of *** *** further reveal the expression mechanism of AP2 in *** petals,we examined the profile of AP2 expression in the inner and outer petals of‘ZiFengyu’at various developmental stages using qRT-PCR and BSP+Miseq methylation *** on our data,the AP2 levels in the outer petals were obviously increased,relative to the inner *** addition,the S3 levels at the bloom stage were significantly higher than at the flower-bud stage S1,thereby promoting bloom stage S2,while declining stage *** chromosome walking,the 2000 bp of the 5′-end upstream promoter region was *** region harbored a CpG island(−665∼−872 bp),with multiple essential transcription factor binding sites(TFBS)such as NF-kappa B,GATA-1,Sp1,and C/*** sequencing revealed 7 methylated CpG sites in the CpG island region of the AP2 promoter,thereinto,the methylation ratio of the CpG-3 site in the inner petals was significantly higher than in the outer *** analysis revealed a negative association between the level of methylation(CpG-3,CpG-6),and AP2 mRNA ***-3 was located on the Sp1 transcription factor binding ***,we speculated that the CpG-3 methylation may inhibit transcription factor Sp1 binding to the gene promoter,thereby regulating AP2 ***,we examined the role of AP2 in the determination of flower patterns in *** conclusion will provide theoretical guidance for the molecular breeding of the flower pattern in ***.
This research is concerned with the following question: How a model trained on mental state detection using stress inducer X would perform on detecting a stress stimulated by inducer Y? This is a scenario that can be ...
详细信息
Production prediction is crucial for the recovery of hydrocarbon ***,accurate and rapid production forecasting remains challenging for unconventional reservoirs due to the complexity of the percolation process and the...
详细信息
Production prediction is crucial for the recovery of hydrocarbon ***,accurate and rapid production forecasting remains challenging for unconventional reservoirs due to the complexity of the percolation process and the scarcity of available *** address this problem,a novel model combining a long short-term memory network(LSTM)and support vector regression(SVR)was proposed to forecast tight oil *** variables,the tubing head pressure,nozzle size,and water rate were utilized as the inputs of the presented machine-learning workflow to account for the influence of operational *** time-series response of tight oil production was the output and was predicted by the optimized LSTM *** SVR-based residual correction model was constructed and embedded with LSTM to increase the prediction *** studies were carried out to verify the feasibility of the proposed method using data from two wells in the Ma-18 block of the Xinjiang *** curve analysis(DCA)methods,LSTM and artificial neural network(ANN)models were also applied in this study and compared with the LSTM-SVR model to prove its *** was demonstrated that introducing residual correction with the newly proposed LSTM-SVR model can effectively improve prediction *** LSTM-SVR model of Well A produced the lowest prediction root mean square error(RMSE)of 5.42,while the RMSE of Arps,PLE Duong,ANN,and LSTM were 5.84,6.65,5.85,8.16,and 7.70,*** RMSE of Well B of LSTM-SVR model is 0.94,while the RMSE of ANN,and LSTM were 1.48,and 2.32.
Aiming at the non-linear and strong coupling characteristics of quadrotor,an improved active disturbance rejection attitude controller was designed in this ***,the nonlinear mathematical model of the quedrotor was est...
详细信息
Aiming at the non-linear and strong coupling characteristics of quadrotor,an improved active disturbance rejection attitude controller was designed in this ***,the nonlinear mathematical model of the quedrotor was established,and then the each link of the traditional active disturbance rejection control(ADRC) was simplified by using the inverse hyperbolic sine function ***,the control effects of the improved ADRC and the traditional ADRC were simulated and verified under the same simulation *** results showed that,compared with the traditional ADRC,the difficulty of parameter tuning of the improved ADRC had been reduced,and the control accuracy had been improved.
We propose a technology called BBCube 3D for AI and HPC applications, which need high bandwidth and power efficiency. BBCube 3D is constructed by heterogeneous 3D integration in which xPU (CPU, GPU etc.) chiplets and ...
We propose a technology called BBCube 3D for AI and HPC applications, which need high bandwidth and power efficiency. BBCube 3D is constructed by heterogeneous 3D integration in which xPU (CPU, GPU etc.) chiplets and DRAM wafers are stacked using a combination of bumpless Wafer-on-Wafer and Chip-on-Wafer. BBCube 3D has the potential to achieve a bandwidth 30 times higher than DDR5 and four times higher than HBM2E with an bit access energy 1/20th that of DDR5 and 1/5th that of HBM2E.
Spinel cobalt oxide(Co_(3)O_(4)),consisting of tetrahedral Co^(2+)(CoTd)and octahedral Co^(3+)(CoOh),is considered as promising earth-abundant electrocatalyst for chlorine evolution reaction(CER).Identifying the catal...
详细信息
Spinel cobalt oxide(Co_(3)O_(4)),consisting of tetrahedral Co^(2+)(CoTd)and octahedral Co^(3+)(CoOh),is considered as promising earth-abundant electrocatalyst for chlorine evolution reaction(CER).Identifying the catalytic contribution of geometric Co site in the electrocatalytic CER plays a pivotal role to precisely modulate electronic configuration of active Co sites to boost ***,combining density functional theory calculations and experiment results assisted with operando analysis,we found that the Co_(Oh) site acts as the main active site for CER in spinel Co_(3)O_(4),which shows better Cl^(-)adsorption and more moderate intermediate adsorption toward CER than CoTd site,and does not undergo redox transition under CER condition at applied *** by above findings,the oxygen vacancies were further introduced into the Co_(3)O_(4) to precisely manipulate the electronic configuration of Co_(Oh) to boost Cl^(-)adsorption and optimize the reaction path of CER and thus to enhance the intrinsic CER activity *** work figures out the importance of geometric configuration dependent CER activity,shedding light on the rational design of advanced electrocatalysts from geometric configuration optimization at the atomic level.
One of the state-of-the-art direction of arrival (DOA) estimation techniques is formulated as a classification problem using deep learning. However, it inherently suffers from quantization errors during the classifica...
详细信息
ISBN:
(数字)9798331516826
ISBN:
(纸本)9798331516833
One of the state-of-the-art direction of arrival (DOA) estimation techniques is formulated as a classification problem using deep learning. However, it inherently suffers from quantization errors during the classification formulation. This weakness is further amplified in two-dimensional (2D) sound source localization (SSL). To address this limitation in 2D SSL, this paper aims to develop a quantization-error-free training objective, named Unbiased Label Distribution (ULD), along with a corresponding decoding scheme for the predicted distribution. The key idea is to use multiple adjacent classes jointly to eliminate quantization error. Experimental results show that the proposed algorithm significantly breaks the quantization error limit when the classification model achieves high accuracy. It also demonstrates strong robustness in low signal-to-noise ratio, high reverberation, and far-field environments.
暂无评论