arXiv subjects

Yunpeng Li

Publications and source records attributed to Yunpeng Li.

86 records · Page 5Linked to original sources

arXiv2019

From Here to There: Video Inbetweening Using Direct 3D Convolutions

We consider the problem of generating plausible and diverse video sequences, when we are only given a start and an end frame. This task is also known as inbetweening, and it belongs to the broader area of stochastic video generation, which is generally approached by means of recurrent neural networks (RNN). In this paper, we propose instead a fully convolutional model to generate video sequences directly in the pixel domain. We first obtain a latent video representation using a stochastic fusion mechanism that learns how to incorporate information from the start and end frames. Our model learns to produce such latent representation by progressively increasing the temporal resolution, and then decode in the spatiotemporal domain using 3D convolutions. The model is trained end-to-end by minimizing an adversarial loss. Experiments on several widely-used benchmark datasets show that it is able to generate meaningful and diverse in-between video sequences, according to both quantitative and qualitative evaluations.

cs.CV↗

arXiv2019

Invertible Particle Flow-based Sequential MCMC with extension to Gaussian Mixture noise models

Sequential state estimation in non-linear and non-Gaussian state spaces has a wide range of applications in statistics and signal processing. One of the most effective non-linear filtering approaches, particle filtering, suffers from weight degeneracy in high-dimensional filtering scenarios. Several avenues have been pursued to address high-dimensionality. Among these, particle flow particle filters construct effective proposal distributions by using invertible flow to migrate particles continuously from the prior distribution to the posterior, and sequential Markov chain Monte Carlo (SMCMC) methods use a Metropolis-Hastings (MH) accept-reject approach to improve filtering performance. In this paper, we propose to combine the strengths of invertible particle flow and SMCMC by constructing a composite Metropolis-Hastings (MH) kernel within the SMCMC framework using invertible particle flow. In addition, we propose a Gaussian mixture model (GMM)-based particle flow algorithm to construct effective MH kernels for multi-modal distributions. Simulation results show that for high-dimensional state estimation example problems the proposed kernels significantly increase the acceptance rate with minimal additional computational overhead and improve estimation accuracy compared with state-of-the-art filtering algorithms.

stat.ME↗

arXiv2018

An Empirical Study of Generative Models with Encoders

Generative adversarial networks (GANs) are capable of producing high quality image samples. However, unlike variational autoencoders (VAEs), GANs lack encoders that provide the inverse mapping for the generators, i.e., encode images back to the latent space. In this work, we consider adversarially learned generative models that also have encoders. We evaluate models based on their ability to produce high quality samples and reconstructions of real images. Our main contributions are twofold: First, we find that the baseline Bidirectional GAN (BiGAN) can be improved upon with the addition of an autoencoder loss, at the expense of an extra hyper-parameter to tune. Second, we show that comparable performance to BiGAN can be obtained by simply training an encoder to invert the generator of a normal GAN.

stat.ML↗

arXiv2018

Recommending Paths: Follow or Not Follow?

Mobile social network applications constitute an important platform for traffic information sharing, helping users collect and share sensor information about the driving conditions they experience on the traveled path in real time. In this paper we analyse the simple but fundamental model of a platform choosing between two paths: one with known deterministic travel cost and the other that alternates over time between a low and a high random cost states, where the low and the high cost states are only partially observable and perform respectively better and worse on average than the fixed cost path. The more users are routed over the stochastic path, the better the platform can infer its actual state and use it efficiently. At the Nash equilibrium, if asked to take the riskier path, in many cases selfish users will myopically disregard the optimal path suggestions of the platform, leading to a suboptimal system without enough exploration on the stochastic path. We prove the interesting result that if the past collected information is hidden from users, the system becomes incentive compatible and even `sophisticated' users (in the sense that they have full capability to reverse-engineer the platform's recommendation and derive the path state distribution conditional on the recommendation) prefer to follow the platform's recommendations. In a more practical setting where the platform implements a model-free Q-learning algorithm to minimise the social travel cost, our analysis suggests that increasing the accuracy of the learning algorithm increases the range of system parameters for which sophisticated users follow ! the recommendations of the platform, becoming in the limit fully incentive compatible. Finally, we extend the two-path model to include more stochastic paths, and show that incentive compatibility holds under our information restriction mechanism.

cs.GT↗

arXiv2018

BCCNet: Bayesian classifier combination neural network

Machine learning research for developing countries can demonstrate clear sustainable impact by delivering actionable and timely information to in-country government organisations (GOs) and NGOs in response to their critical information requirements. We co-create products with UK and in-country commercial, GO and NGO partners to ensure the machine learning algorithms address appropriate user needs whether for tactical decision making or evidence-based policy decisions. In one particular case, we developed and deployed a novel algorithm, BCCNet, to quickly process large quantities of unstructured data to prevent and respond to natural disasters. Crowdsourcing provides an efficient mechanism to generate labels from unstructured data to prime machine learning algorithms for large scale data analysis. However, these labels are often imperfect with qualities varying among different citizen scientists, which prohibits their direct use with many state-of-the-art machine learning techniques. We describe BCCNet, a framework that simultaneously aggregates biased and contradictory labels from the crowd and trains an automatic classifier to process new data. Our case studies, mosquito sound detection for malaria prevention and damage detection for disaster response, show the efficacy of our method in the challenging context of developing world applications.

stat.ML↗

arXiv2017

Cost-sensitive detection with variational autoencoders for environmental acoustic sensing

Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings. While large-scale acoustic data make manual analysis infeasible, they provide a suitable playground for machine learning approaches. Most existing machine learning techniques developed for environmental acoustic sensing do not provide flexible control of the trade-off between the false positive rate and the false negative rate. This paper presents a cost-sensitive classification paradigm, in which the hyper-parameters of classifiers and the structure of variational autoencoders are selected in a principled Neyman-Pearson framework. We examine the performance of the proposed approach using a dataset from the HumBug project which aims to detect the presence of mosquitoes using sound collected by simple embedded devices.

stat.ML↗

arXiv2017

Mosquito detection with low-cost smartphones: data acquisition for malaria research

Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year. Not only is the prevention of mosquito bites of paramount importance to the reduction of malaria transmission cases, but understanding in more forensic detail the interplay between malaria, mosquito vectors, vegetation, standing water and human populations is crucial to the deployment of more effective interventions. Typically the presence and detection of malaria-vectoring mosquitoes is only quantified by hand-operated insect traps or signified by the diagnosis of malaria. If we are to gather timely, large-scale data to improve this situation, we need to automate the process of mosquito detection and classification as much as possible. In this paper, we present a candidate mobile sensing system that acts as both a portable early warning device and an automatic acoustic data acquisition pipeline to help fuel scientific inquiry and policy. The machine learning algorithm that powers the mobile system achieves excellent off-line multi-species detection performance while remaining computationally efficient. Further, we have conducted preliminary live mosquito detection tests using low-cost mobile phones and achieved promising results. The deployment of this system for field usage in Southeast Asia and Africa is planned in the near future. In order to accelerate processing of field recordings and labelling of collected data, we employ a citizen science platform in conjunction with automated methods, the former implemented using the Zooniverse platform, allowing crowdsourcing on a grand scale.

stat.ML↗

arXiv2017

Particle Filtering with Invertible Particle Flow

A key challenge when designing particle filters in high-dimensional state spaces is the construction of a proposal distribution that is close to the posterior distribution. Recent advances in particle flow filters provide a promising avenue to avoid weight degeneracy; particles drawn from the prior distribution are migrated in the state-space to the posterior distribution by solving partial differential equations. Numerous particle flow filters have been proposed based on different assumptions concerning the flow dynamics. Approximations are needed in the implementation of all of these filters; as a result the articles do not exactly match a sample drawn from the desired posterior distribution. Past efforts to correct the discrepancies involve expensive calculations of importance weights. In this paper, we present new filters which incorporate deterministic particle flows into an encompassing particle filter framework. The valuable theoretical guarantees concerning particle filter performance still apply, but we can exploit the attractive performance of the particle flow methods. The filters we describe involve a computationally efficient weight update step, arising because the embedded particle flows we design possess an invertible mapping property. We evaluate the proposed particle flow particle filters' performance through numerical simulations of a challenging multi-target multi-sensor tracking scenario and complex high-dimensional filtering examples.

stat.ME↗

arXiv2017

Microwave breast cancer detection using Empirical Mode Decomposition features

Microwave-based breast cancer detection has been proposed as a complementary approach to compensate for some drawbacks of existing breast cancer detection techniques. Among the existing microwave breast cancer detection methods, machine learning-type algorithms have recently become more popular. These focus on detecting the existence of breast tumours rather than performing imaging to identify the exact tumour position. A key step of the machine learning approaches is feature extraction. One of the most widely used feature extraction method is principle component analysis (PCA). However, it can be sensitive to signal misalignment. This paper presents an empirical mode decomposition (EMD)-based feature extraction method, which is more robust to the misalignment. Experimental results involving clinical data sets combined with numerically simulated tumour responses show that combined features from EMD and PCA improve the detection performance with an ensemble selection-based classifier.

stat.ML↗

arXiv2016

Dynamic routing for social information sharing

Today mobile users are intensively interconnected thanks to the emerging mobile social networks, where they share location-based information with each other when traveling on different routes and visit different areas of the city. In our model the information collected is aggregated over all users' trips and made publicly available as a public good. Due to information overlap, the total useful content amount increases with the diversity in path choices made by the users, and it is crucial to motivate selfish users to choose different paths despite the potentially higher costs associated with their trips. In this paper we combine the benefits from social information sharing with the fundamental routing problem where a unit mass of non-atomic selfish users decide their trips in a non-cooperative game by choosing between a high-cost and a low-cost path. To remedy the inefficient low-content equilibrium where all users choose to explore a single path (the low-cost path), we propose and analyse two new incentive mechanisms that can be used by the social network application, one based on side payments and the other on restricting access to content for users that choose the low cost path. We also obtain interesting price of anarchy results that show some fundamental tradeoffs between achieving path diversity and maintaining greater user participation, motivating a combined mechanism to further increase the social welfare. Our model extends classical dynamic routing in the case of externalities caused from traffic on different paths of the network.

cs.GT↗

arXiv2015

A New Single-Source Shortest Path Algorithm for Nonnegative Weight Graph

The single-source shortest path problem is a classical problem in the research field of graph algorithm. In this paper, a new single-source shortest path algorithm for nonnegative weight graph is proposed. The algorithm can compress multi-round Fibonacci heap operations to one round to save running time relative to Dijkstra's algorithm using Fibonacci heap. The time complexity of the algorithm is also O(m+nlogn) in the worst case, where m is the number of edges and n is the number of nodes. However, the bound can be linear in some case, for example, when edge weights of a graph are all the same and the hop count of the longest shortest path is much less than n.Based on the theoretical analyses, we demonstrate that the algorithm is faster than Dijkstra's algorithm using Fibonacci heap in average situation when n is large enough.

cs.DS↗

arXiv2015

A New Exact Algorithm for Traveling Salesman Problem with Time Complexity Interval (O(n^4), O(n^3*2^n))

Traveling salesman problem is a NP-hard problem. Until now, researchers have not found a polynomial time algorithm for traveling salesman problem. Among the existing algorithms, dynamic programming algorithm can solve the problem in time O(n^2*2^n) where n is the number of nodes in the graph. The branch-and-cut algorithm has been applied to solve the problem with a large number of nodes. However, branch-and-cut algorithm also has an exponential worst-case running time. In this paper, a new exact algorithm for traveling salesman problem is proposed. The algorithm can be used to solve an arbitrary instance of traveling salesman problem in real life and the time complexity interval of the algorithm is (O(n^4), O(n^3*2^n)). It means that for some instances, the algorithm can find the optimal solution in polynomial time although the algorithm also has an exponential worst-case running time. In other words, the algorithm tells us that not all the instances of traveling salesman problem need exponential time to compute the optimal solution. The algorithm of this paper can not only assist us to solve traveling salesman problem better, but also can assist us to deepen the comprehension of the relationship between NP-complete and P. Therefore, it is considerable in the further research on traveling salesman problem and NP-hard problem.

cs.DS↗

arXiv2014

Defuzzify firstly or finally: Dose it matter in fuzzy DEMATEL under uncertain environment?

Decision-Making Trial and Evaluation Laboratory (DEMATEL) method is widely used in many real applications. With the desirable property of efficient handling with the uncertain information in decision making, the fuzzy DEMATEL is heavily studied. Recently, Dytczak and Ginda suggested to defuzzify the fuzzy numbers firstly and then use the classical DEMATEL to obtain the final result. In this short paper, we show that it is not reasonable in some situations. The results of defuzzification at the first step are not coincide with the results of defuzzification at the final step.It seems that the alternative is to defuzzification in the final step in fuzzy DEMATEL.

cs.AI↗

arXiv2013

A brief network analysis of Artificial Intelligence publication

In this paper, we present an illustration to the history of Artificial Intelligence(AI) with a statistical analysis of publish since 1940. We collected and mined through the IEEE publish data base to analysis the geological and chronological variance of the activeness of research in AI. The connections between different institutes are showed. The result shows that the leading community of AI research are mainly in the USA, China, the Europe and Japan. The key institutes, authors and the research hotspots are revealed. It is found that the research institutes in the fields like Data Mining, Computer Vision, Pattern Recognition and some other fields of Machine Learning are quite consistent, implying a strong interaction between the community of each field. It is also showed that the research of Electronic Engineering and Industrial or Commercial applications are very active in California. Japan is also publishing a lot of papers in robotics. Due to the limitation of data source, the result might be overly influenced by the number of published articles, which is to our best improved by applying network keynode analysis on the research community instead of merely count the number of publish.

cs.AI↗