arXiv subjects

Yun Zhou

Publications and source records attributed to Yun Zhou.

At least 55 records · Page 3Linked to original sources

arXiv2020

Exploring Common and Individual Characteristics of Students via Matrix Recovering

Balancing group teaching and individual mentoring is an important issue in education area. The nature behind this issue is to explore common characteristics shared by multiple students and individual characteristics for each student. Biclustering methods have been proved successful for detecting meaningful patterns with the goal of driving group instructions based on students' characteristics. However, these methods ignore the individual characteristics of students as they only focus on common characteristics of students. In this article, we propose a framework to detect both group characteristics and individual characteristics of students simultaneously. We assume that the characteristics matrix of students' is composed of two parts: one is a low-rank matrix representing the common characteristics of students; the other is a sparse matrix representing individual characteristics of students. Thus, we treat the balancing issue as a matrix recovering problem. The experiment results show the effectiveness of our method. Firstly, it can detect meaningful biclusters that are comparable with the state-of-the-art biclutering algorithms. Secondly, it can identify individual characteristics for each student simultaneously. Both the source code of our algorithm and the real datasets are available upon request.

cs.AI↗

arXiv2020

Exercise Hierarchical Feature Enhanced Knowledge Tracing

Knowledge tracing is a fundamental task in the computer-aid educational system. In this paper, we propose a hierarchical exercise feature enhanced knowledge tracing framework, which could enhance the ability of knowledge tracing by incorporating knowledge distribution, semantic features, and difficulty features from exercise text. Extensive experiments show the high performance of our framework.

cs.CY↗

arXiv2020

DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling

Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering. However, deploying these models in real systems is highly non-trivial due to their exorbitant computational costs. A common remedy to this is knowledge distillation (Hinton et al., 2015), leading to faster inference. However -- as we show here -- existing works are not optimized for dealing with pairs (or tuples) of texts. Consequently, they are either not scalable or demonstrate subpar performance. In this work, we propose DiPair -- a novel framework for distilling fast and accurate models on text pair tasks. Coupled with an end-to-end training strategy, DiPair is both highly scalable and offers improved quality-speed tradeoffs. Empirical studies conducted on both academic and real-world e-commerce benchmarks demonstrate the efficacy of the proposed approach with speedups of over 350x and minimal quality drop relative to the cross-attention teacher BERT model.

cs.CL↗

arXiv2020

A Multi-Agent-Based Rolling Optimization Method for Restoration Scheduling of Electrical Distribution Systems with Distributed Generation

Resilience against major disasters is the most essential characteristic of future electrical distribution systems (EDS). A multi-agent-based rolling optimization method for EDS restoration scheduling is proposed in this paper. When a blackout occurs, considering the risk of losing the centralized authority due to the failure of the common core communication network, the agents available after disasters or cyber-attacks identify the communication-connected parts (CCPs) in the EDS with distributed communication. A multi-time interval optimization model is formulated and solved by the agents for the restoration scheduling of a CCP. A rolling optimization process for the entire EDS restoration is proposed. During the scheduling/rescheduling in the rolling process, the CCPs in the EDS are reidentified and the restoration schedules for the CCPs are updated. Through decentralized decision-making and rolling optimization, EDS restoration scheduling can automatically start and periodically update itself, providing effective solutions for EDS restoration scheduling in a blackout event. A modified IEEE 123-bus EDS is utilized to demonstrate the effectiveness of the proposed method.

eess.SP↗

arXiv2020

Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition

Despite the recent success of deep learning in continuous sign language recognition (CSLR), deep models typically focus on the most discriminative features, ignoring other potentially non-trivial and informative contents. Such characteristic heavily constrains their capability to learn implicit visual grammars behind the collaboration of different visual cues (i,e., hand shape, facial expression and body posture). By injecting multi-cue learning into neural network design, we propose a spatial-temporal multi-cue (STMC) network to solve the vision-based sequence learning problem. Our STMC network consists of a spatial multi-cue (SMC) module and a temporal multi-cue (TMC) module. The SMC module is dedicated to spatial representation and explicitly decomposes visual features of different cues with the aid of a self-contained pose estimation branch. The TMC module models temporal correlations along two parallel paths, i.e., intra-cue and inter-cue, which aims to preserve the uniqueness and explore the collaboration of multiple cues. Finally, we design a joint optimization strategy to achieve the end-to-end sequence learning of the STMC network. To validate the effectiveness, we perform experiments on three large-scale CSLR benchmarks: PHOENIX-2014, CSL and PHOENIX-2014-T. Experimental results demonstrate that the proposed method achieves new state-of-the-art performance on all three benchmarks.

cs.CV↗

arXiv2020

Topological valley transport under long-range deformations

Edge states protected by bulk topology of photonic crystals show robustness against short-range disorder, making robust information transfer possible. Here, topological photonic crystals under long-range deformations are investigated. Vertices of each regular hexagon in a honeycomb crystalline structure are shifted randomly to establish a deformed system. By increasing the degree of random deformations, a transition from an ordered system to an amorphous system are investigated, where the close of topological bandgap is clearly shown. We further present comprehensive investigations into excitation methods of the proposed deformed system. Due to the lack of strict periodicity, excitation of topological edge modes becomes difficult. Chiral and linearly polarized sources as two different methods are investigated respectively. It is found that chiral sources are sensitive and rely on the ordered lattice. Even a weak long-range deformation can bring fluctuations to transmission. We further designed and fabricated metal-dielectric-metal sandwich-like samples working in the microwave band. Using linearly polarized source, we detected the existence of topological transport in the deformed system. This work investigates excitation and robustness of bulk topology against long-range deformations and may open the way for exploiting topological properties of materials with a deformed lattice.

physics.optics↗

arXiv2019

A novel linear battery energy storage system (BESS) life loss calculation model for BESS-integrated wind farm in scheduled power tracking

Recently, rapid development of battery technology makes it feasible to integrate renewable generations with battery energy storage system (BESS). The consideration of BESS life loss for different BESS application scenarios is economic imperative. In this paper, a novel linear BESS life loss calculation model for BESS-integrated wind farm in scheduled power tracking is proposed. Firstly, based on the life cycle times-depth of discharge (DOD) relation-curve, the BESS life loss coefficient for unit throughput energy with different state of charge (SOC) can be determined from the life cycle times-DOD relation-curve fitting function directly. Secondly, as unidirectional variation of SOC in a single time step, the BESS life loss can be calculated through integration of the life loss coefficient-SOC relation function. A linear BESS life loss calculation model is established through self-optimal piecewise linearization of the primitive function of the life loss coefficient-SOC relation function. Thirdly, the proposed life loss calculation model is incorporated in the BESS-integrated wind farm scheduled power tracking optimization. Case studies demonstrate that with the proposed method, the BESS life loss item can be incorporated in the optimization model effectively, and the scheduled power tracking cost of the BESS-integrated wind farm can be determined and optimized more comprehensively.

eess.SP↗

arXiv2019

Load Forecasting Model and Day-ahead Operation Strategy for City-located EV Quick Charge Stations

Charging demands of electric vehicles (EVs) are sharply increasing due to the rapid development of EVs. Hence, reliable and convenient quick charge stations are required to respond to the needs of EV drivers. Due to the uncertainty of EV charging loads, load forecasting becomes vital for the operation of quick charge stations to formulate the day-ahead plan. In this paper, based on trip chain theory and EV user behaviour, an EV charging load forecasting model is established for quick charge station operators. This model is capable of forecasting the charging demand of a city-located quick charge station during the next day, where the Monte-Carlo simulation method is applied. Furthermore, based on the forecasting model, a day-ahead profit-oriented operation strategy for such stations is derived. The simulation results support the effectiveness of this forecasting model and the operation strategy. The conclusions of this paper are as follows: 1) The charging load forecasting model ensures operators to grasp the feature of the charging load of the next day. 2) The revenue of the quick charge station can be dramatically increased by applying the proposed day-head operation strategy.

eess.SY↗

arXiv2019

Optimal Decision Making Model of Battery Energy Storage-Assisted Electric Vehicle Charging Station Considering Incentive Demand Response

Considering large scale implementation of electric vehicles (EVs), public EV charging stations are served as fuel tanks for EVs to meet the need of longer travelling distance and overcome the shortage of private charging piles. The allocation of local battery energy storage (BES) can enhance the flexibility of the EV charging station. This paper proposes an optimal decision making model of the BES-assisted EV charging station considering the incentive demand response. Firstly, the detailed models of the BES-assisted EV charging station are presented. Secondly, as a representative incentive demand response, the emergency demand response (EDR) model is introduced. Thirdly, based on the charging load forecast data, an optimal decision making model of the BES-assisted EV charging station considering the EDR to maximize the charging station's operating profit is established. Finally, the feasibility of the proposed method is verified through case studies. The conclusions of this paper are as follows: 1) Through the optimal decision making model, correct and profitable EDR participation decision can be determined for the BES-assisted EV charging station effectively. 2) Local BES in the EV charging station can improve the charging station's ability to participate in the EDR.

eess.SY↗

arXiv2019

Spin-momentum locked modes on anti-phase boundaries in photonic crystals

An anti-phase boundary is formed by shifting a portion of photonic crystal lattice along the direction of periodicity. A spinning magnetic dipole is applied to excite edge modes on the anti-phase boundary. We show the unidirectional propagation of the edge modes which is also known as spin-momentum locking. Band inversion of the edge modes is discovered when we sweep the geometrical parameters, which leads to a change in the propagation direction. Also, an optimized source is applied to excite the unidirectional edge mode with high directivity.

physics.optics↗

arXiv2019

Energy Flux in Hierarchical Equations of Motion Method and Its Application to a Three-Level Heat Engine

We derive the formula of energy flux for the hierarchical equations of motion (HEOM) method with the help of stochastic decoupling technique. The resulting expression is a combination of the terms in the first two layers of the hierarchy. The formula is applied to a three-level "heat engine" coupled respectively to three baths, of which two for heat sources and one for work dump. All the three baths are modeled by collections of harmonic oscillators. We illustrate the proper parameterizing to converge the third bath to the "work-dump" limit. As an example, the effect of the engine parameters on working efficiency is studied.

cond-mat.stat-mech↗

arXiv2018

A Multi-step Piecewise Linear Approximation Based Solution for Load Pick-up Problem in Electrical Distribution System

The load pick-up (LPP) problem searches the optimal configuration of the electrical distribution system (EDS), aiming to minimize the power loss or provide maximum power to the load ends. The piecewise linearization (PWL) approximation method can be used to tackle the nonlinearity and nonconvexity in network power flow (PF) constraints, and transform the LPP model into a mixed-integer linear programming model (LPP-MILP model).However, for the PWL approximation based PF constraints, big linear approximation errors will affect the accuracy and feasibility of the LPP-MILP model's solving results. And the long modeling and solving time of the direct solution procedure of the LPP-MILP model may affect the applicability of the LPP optimization scheme. This paper proposes a multi-step PWL approximation based solution for the LPP problem in the EDS. In the proposed multi-step solution procedure, the variable upper bounds in the PWL approximation functions are dynamically renewed to reduce the approximation errors effectively. And the multi-step solution procedure can significantly decrease the modeling and solving time of the LPP-MILP model, which ensure the applicability of the LPP optimization scheme. For the two main application schemes for the LPP problem (i.e. network optimization reconfiguration and service restoration), the effectiveness of the proposed method is demonstrated via case studies using a real 13-bus EDS and a real 1066-bus EDS.

math.OC↗

arXiv2018

Dynamic Type Matching

We consider an intermediary's problem of dynamically matching demand and supply of heterogeneous types in a periodic-review fashion. More specifically, there are two disjoint sets of demand and supply types, and a reward associated with each possible matching of a demand type and a supply type. In each period, demand and supply of various types arrive in random quantities. The platform's problem is to decide on the optimal matching policy to maximize the total discounted rewards minus costs, given that unmatched demand and supply will incur waiting or holding costs, and will be carried over to the next period (with abandonment). For this dynamic matching problem, we provide sufficient conditions on matching rewards such that the optimal matching policy follows a priority hierarchy among possible matching pairs. We show those conditions are satisfied by vertically and unidirectionally horizontally differentiated types, for which quality and distance determine priority, respectively. As a result of the priority property, the optimal matching policy boils down to a match-down-to threshold structure when considering a specific pair of demand and supply types in the priority hierarchy.

math.OC↗

arXiv2018

Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution

Convolutional neural networks (CNNs) have demonstrated superior performance in super-resolution (SR). However, most CNN-based SR methods neglect the different importance among feature channels or fail to take full advantage of the hierarchical features. To address these issues, this paper presents a novel recursive unit. Firstly, at the beginning of each unit, we adopt a compact channel attention mechanism to adaptively recalibrate the channel importance of input features. Then, the multi-level features, rather than only deep-level features, are extracted and fused. Additionally, we find that it will force our model to learn more details by using the learnable upsampling method (i.e., transposed convolution) only on residual branch (instead of using it both on residual branch and identity branch) while using the bicubic interpolation on the other branch. Analytic experiments show that our method achieves competitive results compared with the state-of-the-art methods and maintains faster speed as well.

cs.CV↗

arXiv2018

Topologically protected pseudospins in 2D spring-mass system

It is proposed that a lattice, with constituent masses and spring constants, may be considered as a model system for topological matter. For instance, a relative variation of the inter- and intra-unit cell spring constants can be used to create, tune, and invert band structure. Such an aspect is obtained while preserving time reversal symmetry, and consequently emulates the quantum spin Hall effect. The modal displacement fields of the mass-spring lattice were superposed so to yield pseudospin fields, with positive or negative group velocity. Considering that harmonic oscillators are the basis of classical and quantum excitations over a range of physical systems, the spring-mass system yields further insight into the constituents and possible utility of topological material.

cond-mat.mes-hall↗

arXiv2018

Self-optimal Piecewise Linearization Based Network Power Flow Constraints in Electrical Distribution System Optimization

As a representative mathematical expression of power flow (PF) constraints in electrical distribution system (EDS), the piecewise linearization (PWL) based PF constraints have been widely used in different EDS optimization scenarios. However, the linearized approximation errors originating from the currently-used PWL approximation function can be very large and thus affect the applicability of the PWL based PF constraints. This letter analyzes the approximation error self-optimal (ESO) condition of the PWL approximation function, refines the PWL function formulas, and proposes the self-optimal (SO)-PWL based PF constraints in EDS optimization which can ensure the minimum approximation errors. Numerical results demonstrate the effectiveness of the proposed method.

math.OC↗

arXiv2017

Providing Effective Real-time Feedback in Simulation-based Surgical Training

Virtual reality simulation is becoming popular as a training platform in surgical education. However, one important aspect of simulation-based surgical training that has not received much attention is the provision of automated real-time performance feedback to support the learning process. Performance feedback is actionable advice that improves novice behaviour. In simulation, automated feedback is typically extracted from prediction models trained using data mining techniques. Existing techniques suffer from either low effectiveness or low efficiency resulting in their inability to be used in real-time. In this paper, we propose a random forest based method that finds a balance between effectiveness and efficiency. Experimental results in a temporal bone surgery simulation show that the proposed method is able to extract highly effective feedback at a high level of efficiency.

cs.AI↗

arXiv2017

Adversarial Generation of Real-time Feedback with Neural Networks for Simulation-based Training

Simulation-based training (SBT) is gaining popularity as a low-cost and convenient training technique in a vast range of applications. However, for a SBT platform to be fully utilized as an effective training tool, it is essential that feedback on performance is provided automatically in real-time during training. It is the aim of this paper to develop an efficient and effective feedback generation method for the provision of real-time feedback in SBT. Existing methods either have low effectiveness in improving novice skills or suffer from low efficiency, resulting in their inability to be used in real-time. In this paper, we propose a neural network based method to generate feedback using the adversarial technique. The proposed method utilizes a bounded adversarial update to minimize a L1 regularized loss via back-propagation. We empirically show that the proposed method can be used to generate simple, yet effective feedback. Also, it was observed to have high effectiveness and efficiency when compared to existing methods, thus making it a promising option for real-time feedback generation in SBT.

cs.LG↗