arXiv subjects

Jie Li

Publications and source records attributed to Jie Li.

At least 667 records · Page 37Linked to original sources

arXiv2019

Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning

Heating, Ventilation, and Air Conditioning (HVAC) is extremely energy-consuming, accounting for 40% of total building energy consumption. Therefore, it is crucial to design some energy-efficient building thermal control policies which can reduce the energy consumption of HVAC while maintaining the comfort of the occupants. However, implementing such a policy is challenging, because it involves various influencing factors in a building environment, which are usually hard to model and may be different from case to case. To address this challenge, we propose a deep reinforcement learning based framework for energy optimization and thermal comfort control in smart buildings. We formulate the building thermal control as a cost-minimization problem which jointly considers the energy consumption of HVAC and the thermal comfort of the occupants. To solve the problem, we first adopt a deep neural network based approach for predicting the occupants' thermal comfort, and then adopt Deep Deterministic Policy Gradients (DDPG) for learning the thermal control policy. To evaluate the performance, we implement a building thermal control simulation system and evaluate the performance under various settings. The experiment results show that our method can improve the thermal comfort prediction accuracy, and reduce the energy consumption of HVAC while improving the occupants' thermal comfort.

eess.SY↗

arXiv2018

Kepler Data Validation II -- Transit Model Fitting and Multiple-Planet Search

This paper discusses the transit model fitting and multiple-planet search algorithms and performance of the Kepler Science Data Processing Pipeline, developed by the Kepler Science Operations Center (SOC). Threshold Crossing Events (TCEs), which are transit candidate events, are generated by the Transiting Planet Search (TPS) component of the pipeline and subsequently processed in the Data Validation (DV) component. The transit model is used in DV to fit TCEs in order to characterize planetary candidates and to derive parameters that are used in various diagnostic tests to classify them. After the signature associated with the TCE is removed from the light curve of the target star, the residual light curve goes through TPS again to search for additional TCEs. The iterative process of transit model fitting and multiple-planet search continues until no TCE is generated from the residual light curve or an upper limit is reached. The transit model fitting and multiple-planet search performance of the final release (9.3, January 2016) of the pipeline is demonstrated with the results of the processing of 4 years (17 quarters) of flight data from the primary Kepler Mission. The transit model fitting results are accessible from the NASA Exoplanet Archive. The final version of the SOC codebase is available through GitHub.

astro-ph.IM↗

arXiv2018

Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context

The use of future contextual information is typically shown to be helpful for acoustic modeling. Recently, we proposed a RNN model called minimal gated recurrent unit with input projection (mGRUIP), in which a context module namely temporal convolution, is specifically designed to model the future context. This model, mGRUIP with context module (mGRUIP-Ctx), has been shown to be able of utilizing the future context effectively, meanwhile with quite low model latency and computation cost. In this paper, we continue to improve mGRUIP-Ctx with two revisions: applying BN methods and enlarging model context. Experimental results on two Mandarin ASR tasks (8400 hours and 60K hours) show that, the revised mGRUIP-Ctx outperform LSTM with a large margin (11% to 38%). It even performs slightly better than a superior BLSTM on the 8400h task, with 33M less parameters and just 290ms model latency.

cs.CL↗

arXiv2018

Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning

The explosive growth of digital images in video surveillance and social media has led to the significant need for efficient search of persons of interest in law enforcement and forensic applications. Despite tremendous progress in primary biometric traits (e.g., face and fingerprint) based person identification, a single biometric trait alone cannot meet the desired recognition accuracy in forensic scenarios. Tattoos, as one of the important soft biometric traits, have been found to be valuable for assisting in person identification. However, tattoo search in a large collection of unconstrained images remains a difficult problem, and existing tattoo search methods mainly focus on matching cropped tattoos, which is different from real application scenarios. To close the gap, we propose an efficient tattoo search approach that is able to learn tattoo detection and compact representation jointly in a single convolutional neural network (CNN) via multi-task learning. While the features in the backbone network are shared by both tattoo detection and compact representation learning, individual latent layers of each sub-network optimize the shared features toward the detection and feature learning tasks, respectively. We resolve the small batch size issue inside the joint tattoo detection and compact representation learning network via random image stitch and preceding feature buffering. We evaluate the proposed tattoo search system using multiple public-domain tattoo benchmarks, and a gallery set with about 300K distracter tattoo images compiled from these datasets and images from the Internet. In addition, we also introduce a tattoo sketch dataset containing 300 tattoos for sketch-based tattoo search. Experimental results show that the proposed approach has superior performance in tattoo detection and tattoo search at scale compared to several state-of-the-art tattoo retrieval algorithms.

cs.CV↗

arXiv2018

Magnon-photon-phonon entanglement in cavity magnomechanics

We show how to generate tripartite entanglement in a cavity magnomechanical system which consists of magnons, cavity microwave photons, and phonons. The magnons are embodied by a collective motion of a large number of spins in a macroscopic ferrimagnet, and are driven directly by an electromagnetic field. The cavity photons and magnons are coupled via magnetic dipole interaction, and the magnons and phonons are coupled via magnetostrictive (radiation pressure-like) interaction. We show optimal parameter regimes for achieving the tripartite entanglement where magnons, cavity photons, and phonons are entangled with each other, and we further prove that the steady state of the system is a genuinely tripartite entangled state. The entanglement is robust against temperature. Our results indicate that cavity magnomechanical systems could provide a promising platform for the study of macroscopic quantum phenomena.

quant-ph↗

arXiv2018

Linear Coded Caching Scheme for Centralized Networks

Coded caching systems have been widely studied to reduce the data transmission during the peak traffic time. In practice, two important parameters of a coded caching system should be considered, i.e., the rate which is the maximum amount of the data transmission during the peak traffic time, and the subpacketization level, the number of divided packets of each file when we implement a coded caching scheme. We prefer to design a scheme with rate and packet number as small as possible since they reflect the transmission efficiency and complexity of the caching scheme, respectively. In this paper, we first characterize a coded caching scheme from the viewpoint of linear algebra and show that designing a linear coded caching scheme is equivalent to constructing three classes of matrices satisfying some rank conditions. Then based on the invariant linear subspaces and combinatorial design theory, several classes of new coded caching schemes over $\mathbb{F}_2$ are obtained by constructing these three classes of matrices. It turns out that the rate of our new rate is the same as the scheme construct by Yan et al. (IEEE Trans. Inf. Theory 63, 5821-5833, 2017), but the packet number is significantly reduced. A concatenating construction then is used for flexible number of users. Finally by means of these matrices, we show that the minimum storage regenerating codes can also be used to construct coded caching schemes.

cs.IT↗

arXiv2018

Channel-wise and Spatial Feature Modulation Network for Single Image Super-Resolution

The performance of single image super-resolution has achieved significant improvement by utilizing deep convolutional neural networks (CNNs). The features in deep CNN contain different types of information which make different contributions to image reconstruction. However, most CNN-based models lack discriminative ability for different types of information and deal with them equally, which results in the representational capacity of the models being limited. On the other hand, as the depth of neural networks grows, the long-term information coming from preceding layers is easy to be weaken or lost in late layers, which is adverse to super-resolving image. To capture more informative features and maintain long-term information for image super-resolution, we propose a channel-wise and spatial feature modulation (CSFM) network in which a sequence of feature-modulation memory (FMM) modules is cascaded with a densely connected structure to transform low-resolution features to high informative features. In each FMM module, we construct a set of channel-wise and spatial attention residual (CSAR) blocks and stack them in a chain structure to dynamically modulate multi-level features in a global-and-local manner. This feature modulation strategy enables the high contribution information to be enhanced and the redundant information to be suppressed. Meanwhile, for long-term information persistence, a gated fusion (GF) node is attached at the end of the FMM module to adaptively fuse hierarchical features and distill more effective information via the dense skip connections and the gating mechanism. Extensive quantitative and qualitative evaluations on benchmark datasets illustrate the superiority of our proposed method over the state-of-the-art methods.

cs.CV↗

arXiv2018

Spatial Variable Selection and An Application to Virginia Lyme Disease Emergence

Lyme disease is an infectious disease that is caused by a bacterium called Borrelia burgdorferi sensu stricto. In the United States, Lyme disease is one of the most common infectious diseases. The major endemic areas of the disease are New England, Mid-Atlantic, East-North Central, South Atlantic, and West North-Central. Virginia is on the front-line of the disease's diffusion from the northeast to the south. One of the research objectives for the infectious disease community is to identify environmental and economic variables that are associated with the emergence of Lyme disease. In this paper, we use a spatial Poisson regression model to link the spatial disease counts and environmental and economic variables, and develop a spatial variable selection procedure to effectively identify important factors by using an adaptive elastic net penalty. The proposed methods can automatically select important covariates, while adjusting for possible spatial correlations of disease counts. The performance of the proposed method is studied and compared with existing methods via a comprehensive simulation study. We apply the developed variable selection methods to the Virginia Lyme disease data and identify important variables that are new to the literature. Supplementary materials for this paper are available online.

stat.AP↗

arXiv2018

Restricting Greed in Training of Generative Adversarial Network

Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning. Variations of GAN have achieved competitive results on specific tasks. However, the stability of training and diversity of generated instances are still worth studying further. Training of GAN can be thought of as a greedy procedure, in which the generative net tries to make the locally optimal choice (minimizing loss function of discriminator) in each iteration. Unfortunately, this often makes generated data resemble only a few modes of real data and rotate between modes. To alleviate these problems, we propose a novel training strategy to restrict greed in training of GAN. With help of our method, the generated samples can cover more instance modes with more stable training process. Evaluating our method on several representative datasets, we demonstrate superiority of improved training strategy on typical GAN models with different distance metrics.

cs.CV↗

arXiv2018

Spatial-Spectral Fusion by Combining Deep Learning and Variation Model

In the field of spatial-spectral fusion, the model-based method and the deep learning (DL)-based method are state-of-the-art. This paper presents a fusion method that incorporates the deep neural network into the model-based method for the most common case in the spatial-spectral fusion: PAN/multispectral (MS) fusion. Specifically, we first map the gradient of the high spatial resolution panchromatic image (HR-PAN) and the low spatial resolution multispectral image (LR-MS) to the gradient of the high spatial resolution multispectral image (HR-MS) via a deep residual convolutional neural network (CNN). Then we construct a fusion framework by the LR-MS image, the gradient prior learned from the gradient network, and the ideal fused image. Finally, an iterative optimization algorithm is used to solve the fusion model. Both quantitative and visual assessments on high-quality images from various sources demonstrate that the proposed fusion method is superior to all the mainstream algorithms included in the comparison in terms of overall fusion accuracy.

cs.CV↗

arXiv2018

A Generic Transformation to Enable Optimal Repair in MDS Codes for Distributed Storage Systems

We propose a generic transformation that can convert any nonbinary $(n=k+r,k)$ maximum distance separable (MDS) code into another $(n,k)$ MDS code over the same field such that 1) some arbitrarily chosen $r$ nodes have the optimal repair bandwidth and the optimal rebuilding access, 2) for the remaining $k$ nodes, the normalized repair bandwidth and the normalized rebuilding access (over the file size) are preserved, 3) the sub-packetization level is increased only by a factor of $r$. Two immediate applications of this generic transformation are then presented. The first application is that we can transform any nonbinary MDS code with the optimal repair bandwidth or the optimal rebuilding access for the systematic nodes only, into a new MDS code which possesses the corresponding repair optimality for all nodes. The second application is that by applying the transformation multiple times, any nonbinary $(n,k)$ scalar MDS code can be converted into an $(n,k)$ MDS code with the optimal repair bandwidth and the optimal rebuilding access for all nodes, or only a subset of nodes, whose sub-packetization level is also optimal.

cs.IT↗

arXiv2018

Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multi-scale feature extraction and multi-level feature representation are respectively employed to capture both the multi-scale spatial-spectral feature and fuse the feature representations with different levels for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.

cs.CV↗

arXiv2018

Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint

In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods. Specifically, we perform the network feed-forwarding in a bottom-up manner, and then parse the poses with bounding box constraints in a top-down manner. In contrast to the previous top-down methods, our method is robust to bounding box shift and tightness. We extract features from an original image by a residual network and train the network to learn both the confidence maps of joints and the connection relationships between joints. During testing, the predicted confidence maps, the connection relationships and the bounding boxes are used to parse the poses of all persons. The experimental results showed that our method learns more accurate human poses especially in challenging situations and gains better time performance, compared with the bottom-up and the top-down methods.

cs.CV↗

arXiv2018

Generation and detection of non-Gaussian phonon-added coherent states in optomechanical systems

Adding excitations on a coherent state provides an effective way to observe nonclassical properties of radiation fields. Here we describe and analyse how to apply this concept to the motional state of a mechanical oscillator and present a full scheme to prepare non-Gaussian {\it phonon}-added coherent states of the mechanical motion in cavity optomechanics. We first generate a mechanical coherent state using electromagnetically induced transparency. We then add a single phonon onto the coherent state via optomechanical parametric down-conversion combined with single photon detection. We validate this single-phonon-added coherent state by using a red-detuned beam and reading out the state of the optical output field. This approach allows us to verify nonclassical properties of the phonon state, such as sub-Poissonian character and quadrature squeezing. We further show that our scheme can be directly implemented using existing devices, and is generic in nature and hence applicable to a variety of systems in opto- and electromechanics.

quant-ph↗

arXiv2018

A survey of dimensionality reduction techniques based on random projection

Dimensionality reduction techniques play important roles in the analysis of big data. Traditional dimensionality reduction approaches, such as principal component analysis (PCA) and linear discriminant analysis (LDA), have been studied extensively in the past few decades. However, as the dimensionality of data increases, the computational cost of traditional dimensionality reduction methods grows exponentially, and the computation becomes prohibitively intractable. These drawbacks have triggered the development of random projection (RP) techniques, which map high-dimensional data onto a low-dimensional subspace with extremely reduced time cost. However, the RP transformation matrix is generated without considering the intrinsic structure of the original data and usually leads to relatively high distortion. Therefore, in recent years, methods based on RP have been proposed to address this problem. In this paper, we summarize the methods used in different situations to help practitioners to employ the proper techniques for their specific applications. Meanwhile, we enumerate the benefits and limitations of the various methods and provide further references for researchers to develop novel RP-based approaches.

cs.LG↗

arXiv2018

Gated Recurrent Unit Based Acoustic Modeling with Future Context

The use of future contextual information is typically shown to be helpful for acoustic modeling. However, for the recurrent neural network (RNN), it's not so easy to model the future temporal context effectively, meanwhile keep lower model latency. In this paper, we attempt to design a RNN acoustic model that being capable of utilizing the future context effectively and directly, with the model latency and computation cost as low as possible. The proposed model is based on the minimal gated recurrent unit (mGRU) with an input projection layer inserted in it. Two context modules, temporal encoding and temporal convolution, are specifically designed for this architecture to model the future context. Experimental results on the Switchboard task and an internal Mandarin ASR task show that, the proposed model performs much better than long short-term memory (LSTM) and mGRU models, whereas enables online decoding with a maximum latency of 170 ms. This model even outperforms a very strong baseline, TDNN-LSTM, with smaller model latency and almost half less parameters.

cs.CL↗

arXiv2018

Dynamic physical layer equalization in optical communication networks

In optical transport networks, signal lightpaths between two terminal nodes can be different due to current network conditions. Thus the transmission distance and accumulated dispersion in the lightpath cannot be predicted. Therefore, the adaptive compensation of dynamic dispersion is necessary in such networks to enable flexible routing and switching. In this paper, we present a detailed analysis on the adaptive dispersion compensation using the least-mean-square (LMS) algorithm in coherent optical communication networks. It is found that the variable-step-size LMS equalizer can achieve the same performance with a lower complexity, compared to the traditional LMS algorithm.

cs.IT↗

arXiv2018

Kepler Data Validation I -- Architecture, Diagnostic Tests, and Data Products for Vetting Transiting Planet Candidates

The Kepler Mission was designed to identify and characterize transiting planets in the Kepler Field of View and to determine their occurrence rates. Emphasis was placed on identification of Earth-size planets orbiting in the Habitable Zone of their host stars. Science data were acquired for a period of four years. Long-cadence data with 29.4 min sampling were obtained for ~200,000 individual stellar targets in at least one observing quarter in the primary Kepler Mission. Light curves for target stars are extracted in the Kepler Science Data Processing Pipeline, and are searched for transiting planet signatures. A Threshold Crossing Event is generated in the transit search for targets where the transit detection threshold is exceeded and transit consistency checks are satisfied. These targets are subjected to further scrutiny in the Data Validation (DV) component of the Pipeline. Transiting planet candidates are characterized in DV, and light curves are searched for additional planets after transit signatures are modeled and removed. A suite of diagnostic tests is performed on all candidates to aid in discrimination between genuine transiting planets and instrumental or astrophysical false positives. Data products are generated per target and planet candidate to document and display transiting planet model fit and diagnostic test results. These products are exported to the Exoplanet Archive at the NASA Exoplanet Science Institute, and are available to the community. We describe the DV architecture and diagnostic tests, and provide a brief overview of the data products. Transiting planet modeling and the search for multiple planets on individual targets are described in a companion paper. The final revision of the Kepler Pipeline code base is available to the general public through GitHub. The Kepler Pipeline has also been modified to support the TESS Mission which will commence in 2018.

astro-ph.EP↗