Searcharxiv⌕ Search

arXiv subjects

Yifan Jin

Publications and source records attributed to Yifan Jin.

24 records · Page 2Linked to original sources

AlphaMLDigger: A Novel Machine Learning Solution to Explore Excess Return on Investment

How to quickly and automatically mine effective information and serve investment decisions has attracted more and more attention from academia and industry. And new challenges have arisen with the global pandemic. This paper proposes a two-phase AlphaMLDigger that effectively finds excessive returns in a highly fluctuated market. In phase 1, a deep sequential natural language processing (NLP) model is proposed to transfer Sina Microblog blogs to market sentiment. In phase 2, the predicted market sentiment is combined with social network indicator features and stock market history features to predict the stock movements with different Machine Learning models and optimizers. The results show that the ensemble models achieve an accuracy of 0.984 and significantly outperform the baseline model. In addition, we find that COVID-19 brings data shift to China's stock market.

q-fin.CP↗

Characterization of the transient response of diamond sensors to collimated, sub-ps, 1 GeV electron bunches

Diamond sensors (DS) are widely used as solid-state particle detectors, beam loss monitors, and dosimeters in high-radiation environments, e.g., particle colliders. We have calibrated our DS with steady $β$- and X-radiation, spanning a dose rate in the range 0.1-100 mGy/s. Here, we report the first systematic characterization of transient responses of DS to collimated, sub-picosecond, 1 GeV electron bunches. These bunches, possessing a charge ranging from tens to hundreds of pC and a size from tens of microns to millimeters, are suitably provided by the FERMI electron linac in Trieste, Italy. The high density of charge carriers generated by ionization in the diamond bulk causes a transient modification of electrical properties of DS (e.g., resistance), which in turn affects the signal shape. We have modeled a two-step numerical approach, simulating the effects on the signal of both the evolution of charge carrier density in the diamond bulk and the changes in the circuit parameters. This approach interprets features observed in our experimental results to a great extent.

physics.ins-det↗

Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest

Medical Relation Extraction (MRE) task aims to extract relations between entities in medical texts. Traditional relation extraction methods achieve impressive success by exploring the syntactic information, e.g., dependency tree. However, the quality of the 1-best dependency tree for medical texts produced by an out-of-domain parser is relatively limited so that the performance of medical relation extraction method may degenerate. To this end, we propose a method to jointly model semantic and syntactic information from medical texts based on causal explanation theory. We generate dependency forests consisting of the semantic-embedded 1-best dependency tree. Then, a task-specific causal explainer is adopted to prune the dependency forests, which are further fed into a designed graph convolutional network to learn the corresponding representation for downstream task. Empirically, the various comparisons on benchmark medical datasets demonstrate the effectiveness of our model.

cs.CL↗

An SBR Based Ray Tracing Channel Modeling Method for THz and Massive MIMO Communications

Terahertz (THz) communication and the application of massive multiple-input multiple-output (MIMO) technology have been proved significant for the sixth generation (6G) communication systems, and have gained global interests. In this paper, we employ the shooting and bouncing ray (SBR) method integrated with acceleration technology to model THz and massive MIMO channel. The results of ray tracing (RT) simulation in this paper, i.e., angle of departure (AoD), angle of arrival (AoA), and power delay profile (PDP) under the frequency band supported by the commercial RT software Wireless Insite (WI) are in agreement with those produced by WI. Based on the Kirchhoff scattering effect on material surfaces and atmospheric absorption loss showing at THz frequency band, the modified propagation models of Fresnel reflection coefficients and free-space attenuation are consistent with the measured results. For massive MIMO, the channel capacity and the stochastic power distribution are analyzed. The results indicate the applicability of SBR method for building deterministic models of THz and massive MIMO channels with extensive functions and acceptable accuracy.

eess.SP↗

Convergence of Contrastive Divergence Algorithm in Exponential Family

The Contrastive Divergence (CD) algorithm has achieved notable success in training energy-based models including Restricted Boltzmann Machines and played a key role in the emergence of deep learning. The idea of this algorithm is to approximate the intractable term in the exact gradient of the log-likelihood function by using short Markov chain Monte Carlo (MCMC) runs. The approximate gradient is computationally-cheap but biased. Whether and why the CD algorithm provides an asymptotically consistent estimate are still open questions. This paper studies the asymptotic properties of the CD algorithm in canonical exponential families, which are special cases of the energy-based model. Suppose the CD algorithm runs $m$ MCMC transition steps at each iteration $t$ and iteratively generates a sequence of parameter estimates $\{θ_t\}_{t \ge 0}$ given an i.i.d. data sample $\{X_i\}_{i=1}^n \sim p_{θ_\star}$. Under conditions which are commonly obeyed by the CD algorithm in practice, we prove the existence of some bounded $m$ such that any limit point of the time average $\left. \sum_{s=0}^{t-1} θ_s \right/ t$ as $t \to \infty$ is a consistent estimate for the true parameter $θ_\star$. Our proof is based on the fact that $\{θ_t\}_{t \ge 0}$ is a homogenous Markov chain conditional on the data sample $\{X_i\}_{i=1}^n$. This chain meets the Foster-Lyapunov drift criterion and converges to a random walk around the Maximum Likelihood Estimate. The range of the random walk shrinks to zero at rate $\mathcal{O}(1/\sqrt[3]{n})$ as the sample size $n \to \infty$.

stat.ML↗

Predictive coupled-cluster isomer orderings for some Si${}_n$C${}_m$ ($m, n\le 12$) clusters; A pragmatic comparison between DFT and complete basis limit coupled-cluster benchmarks

The accurate determination of the preferred ${\rm Si}_{12}{\rm C}_{12}$ isomer is important to guide experimental efforts directed towards synthesizing SiC nano-wires and related polymer structures which are anticipated to be highly efficient exciton materials for opto-electronic devices. In order to definitively identify preferred isomeric structures for silicon carbon nano-clusters, highly accurate geometries, energies and harmonic zero point energies have been computed using coupled-cluster theory with systematic extrapolation to the complete basis limit for set of silicon carbon clusters ranging in size from SiC$_3$ to ${\rm Si}_{12}{\rm C}_{12}$. It is found that post-MBPT(2) correlation energy plays a significant role in obtaining converged relative isomer energies, suggesting that predictions using low rung density functional methods will not have adequate accuracy. Utilizing the best composite coupled-cluster energy that is still computationally feasible, entailing a 3-4 SCF and CCSD extrapolation with triple-$ζ$ (T) correlation, the {\it closo} ${\rm Si}_{12}{\rm C}_{12}$ isomer is identified to be the preferred isomer in support of previous calculations [J. Chem. Phys. 2015, 142, 034303]. Additionally we have investigated more pragmatic approaches to obtaining accurate silicon carbide isomer energies, including the use of frozen natural orbital coupled-cluster theory and several rungs of standard and double-hybrid density functional theory. Frozen natural orbitals as a way to compute post MBPT(2) correlation energy is found to be an excellent balance between efficiency and accuracy.

physics.chem-ph↗