Learn More
A novel semisupervised extreme learning machine (ELM) with clustering discrimination manifold regularization (CDMR) framework named CDMR-ELM is proposed for semisupervised classification. By using unsupervised fuzzy clustering method, CDMR framework integrates clustering discrimination of both labeled and unlabeled data with twinning constraints(More)
Identifying changes in the vibrational signatures of a structure is a promising tool in structural health diagnosis. Neural networks can be used for this purpose. This paper investigates the feasibility of using analytically generated training samples to train neural networks. This network, trained with analytically generated states of damage, was used to(More)
This research proposes a novel framework of final drive simultaneous failure diagnosis containing feature extraction, training paired diagnostic models, generating decision threshold, and recognizing simultaneous failure modes. In feature extraction module, adopt wavelet package transform and fuzzy entropy to reduce noise interference and extract(More)
Fullerene molecules such as C(60) are large nearly spherical shells of carbon atoms. Pairs of such molecules have a strong long-range van der Waals attraction that can produce scattering or binding into molecular crystals. A simplified classical-electrodynamics model for a fullerene is a spherical metal shell, with uniform electron density confined between(More)
Based on traditional Gilbert Cell prototype, a 900 MHz down-conversion mixer which conclude class AB transconductor and LC tank is demonstrated in this paper. The RF, LO and IF port frequencies are 900 MHz, 800 MHz and 100 MHz, respectively. With SMIC 0.18 um process, simulation results show -1.2 dBm of P-ldB compression point and 8.5 dBm of IIP3 with -5(More)
Based on traditional Gilbert Cell prototype, a 5.8 GHz down-conversion mixer which conclude CMOS gm Cell and LC tank is demonstrated in this paper. The RF, LO and IF port frequencies are 5.8 GHz, 5.75 GHz and 50 MHz, respectively. With SMIC 0.18 um process, simulation results show 3.2dB of conversion gain,-0.8dBm of P-1dB compression point and 7.9 dBm of(More)
  • 1