Bin Liu- Ph.D
- Chief Robot Expert at E-surfing Digital Life Tech Co., Ltd.
Bin Liu
- Ph.D
- Chief Robot Expert at E-surfing Digital Life Tech Co., Ltd.
About
103
Publications
32,085
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
771
Citations
Introduction
Bin Liu obtained his Ph.D. in signal and information processing from the Chinese Academy of Sciences in 2009. Since Nov. 2024, he has held a position-chief robot expert, at E-Surfing Digital Life Technology Co., Ltd., a subsidiary of China Telecom Group. Bin's work has largely centered around AI models and algorithms like deep learning, Bayesian methods, reinforcement learning, embodied intelligence, and AI agents. He's now focusing on large pre-trained models and embodied robot systems.
Current institution
E-surfing Digital Life Tech Co., Ltd.
Current position
- Chief Robot Expert
Additional affiliations
April 2020 - February 2021
February 2021 - July 2024
Zhejiang Lab
Position
- Professor & Team Leader & Project Lead
July 2024 - October 2024
Education
September 2004 - January 2009
Publications
Publications (103)
State filtering is a key problem in many signal processing applications. From a series of noisy measurement, one would like to estimate the state of some dynamic system. Existing techniques usually adopt a Gaussian noise assumption which may result in a major degradation in performance when the measurements are with the presence of outliers. A robu...
Averaging neural network weights sampled by a backbone stochastic gradient descent (SGD) is a simple-yet-effective approach to assist the backbone SGD in finding better optima, in terms of generalization. From a statistical perspective, weight-averaging contributes to variance reduction. Recently, a well-established stochastic weight-averaging (SWA...
Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. However, interactions with LLMs can be time-consuming. In many practical scenarios...
The use of time series for sequential online prediction (SOP) has long been a research topic, but achieving robust and computationally efficient SOP with non-stationary time series remains a challenge. This paper reviews a framework, called Bayesian Dynamic Ensemble of Multiple Models (BDEMM), which addresses SOP in a theoretically elegant way, and...
Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling specific target problems, particularly in real-time dynamic environments. Additionally, deploying an LLM-based...
Physics-informed neural networks (PINNs) have emerged as powerful tools for solving a wide range of partial differential equations (PDEs). However, despite their user-friendly interface and broad applicability, PINNs encounter challenges in accurately resolving PDEs, especially when dealing with singular cases that may lead to unsatisfactory local...
Existing large pre-trained models typically map text input to text output in an end-to-end manner, such as ChatGPT, or map a segment of text input to a hierarchy of action decisions, such as OpenVLA. However, humans can simultaneously generate text and actions when receiving specific input signals. For example, a driver can make precise driving dec...
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurrin...
Deep learning has achieved tremendous success in computer vision, while medical image segmentation (MIS) remains a challenge, due to the scarcity of data annotations. Meta-learning techniques for few-shot segmentation (Meta-FSS) have been widely used to tackle this challenge, while they neglect possible distribution shifts between the query image a...
- [...]
Open-World Few-Shot Learning (OFSL) is a crucial research field dedicated to accurately identifying target samples in scenarios where data is limited and labels are unreliable. This research holds significant practical implications and is highly relevant to real-world applications. Recently, the advancements in foundation models like CLIP and DINO...
Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling specific target problems, particularly in real-time dynamic environments. Additionally, deploying an LLM-based...
This code demonstrates the utilization of adaptive annealed importance sampling (AAIS) to sample from a three-dimensional flared helix function, which is treated as an unnormalized target distribution. The AAIS algorithm has been published in the following paper:
@article{liu2014adaptive,
title={Adaptive annealed importance sampling for multimodal...
Deep generative models have been demonstrated as problematic in the unsupervised out-ofdistribution (OOD) detection task, where they tend to assign higher likelihoods to OOD samples. Previous studies on this issue are usually not applicable to the Variational Autoencoder (VAE). As a popular subclass of generative models, the VAE can be effective wi...
This code demonstrates the utilization of adaptive annealed importance sampling (AAIS) to sample from a Rastrigin function, which is treated as an unnormalized target distribution. The AAIS algorithm has been published in the following paper:
[1] Liu, B., Adaptive Annealed Importance Sampling for Multimodal Posterior Exploration and Model Selectio...
Wave propagation problems are typically formulated as partial differential equations (PDEs) on unbounded domains to be solved. The classical approach to solving such problems involves truncating them to problems on bounded domains by designing the artificial boundary conditions or perfectly matched layers, which typically require significant effort...
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently adapt the agent to new tasks by inferring the task representation, and then adjusting the policy based on this i...
Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix builds on CutMix, a simple yet highly effective data augmentation technique that has gained popularity in recent...
Training an ensemble of diverse sub-models has been empirically demonstrated as an effective strategy for improving the adversarial robustness of deep neural networks. However, current ensemble training methods for image recognition typically encode image labels using one-hot vectors, which overlook dependency relationships between the labels. In t...
Ensemble methods are commonly used to enhance the generalization performance of machine learning models. However, they present a challenge in deep learning systems due to the high computational overhead required to train an ensemble of deep neural networks (DNNs). Recent advancements such as fast geometric ensembling (FGE) and snapshot ensembles ha...
This technical report presents our solution to Ball Action Spotting in videos. Our method reached second place in the CVPR'23 SoccerNet Challenge. Details of this challenge can be found at https://www.soccer-net.org/tasks/ball-action-spotting. Our approach is developed based on a baseline model termed E2E-Spot, which was provided by the organizer o...
This technical report presents our Restormer-Plus approach, which was submitted to the GT-RAIN Challenge (CVPR 2023 UG2+ Track 3). Details regarding the challenge are available at http://cvpr2023.ug2challenge.org/track3.html. Restormer-Plus outperformed all other submitted solutions in terms of peak signal-to-noise ratio (PSNR), and ranked 4th in t...
Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix builds on CutMix, a simple yet highly effective data augmentation technique that has gained popularity in recent...
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently adapt the agent to new tasks by inferring the task representation, and then adjusting the policy based on this i...
Deep learning has become the dominating approach for object detection. To achieve accurate fine-grained detection, one needs to employ a large enough model and a vast amount of data annotations. In this paper, we propose a commonsense knowledge inference module (CKIM) which leverages commonsense knowledge to assist a lightweight deep neural network...
Collecting a substantial number of labeled samples is infeasible in many real-world scenarios, thereby bringing out challenges for supervised classification. The research on Few-Shot Classification (FSC) aims to address this issue. Current FSC methods mainly leverage ideas such as meta-learning, self-supervised learning, and data augmentation. Amon...
Deep learning has achieved tremendous success in computer vision, while medical image segmentation (MIS) remains a challenge, due to the scarcity of data annotations. Meta-learning techniques for few-shot segmentation (Meta-FSS) have been widely used to tackle this challenge, while they neglect possible distribution shifts between the query image a...
Training an ensemble of diverse sub-models has been empirically demonstrated as an effective strategy for improving the adversarial robustness of deep neural networks. However, current ensemble training methods for image recognition typically encode image labels using one-hot vectors, which overlook dependency relationships between the labels. In t...
Ensemble methods are commonly used to enhance the generalization performance of machine learning models. However, they present a challenge in deep learning systems due to the high computational overhead required to train an ensemble of deep neural networks (DNNs). Recent advancements such as fast geometric en-sembling (FGE) and snapshot ensembles h...
Averaging neural network weights sampled by a backbone stochastic gradient descent (SGD) is a simple yet effective approach to assist the backbone SGD in finding better optima, in terms of generalization. From a statistical perspective, weight averaging (WA) contributes to variance reduction. Recently, a well-established stochastic weight averaging...
The use of time series for sequential online prediction (SOP) has long been a research topic, but achieving robust and computationally efficient SOP with non-stationary time series remains a challenge. This paper reviews a framework, called Bayesian Dynamic Ensemble of Multiple Models (BDEMM), which addresses SOP in a theoretically elegant way, and...
This letter is concerned with multi-modal data fusion (MMDF) under unexpected modality failures in nonlinear non-Gaussian dynamic processes. An efficient framework to tackle this problem is proposed. In particular, a notion termed modality “
usefulness
,” which takes a value of 1 or 0, is used for indicating whether the observation of this modalit...
This letter is concerned with image classification with deep convolutional neural networks (CNNs). The focus is on the following question: given a set of candidate CNN models, how to select the right one with the best generalization property for the current task? Present model selection methods require access to a batch of labeled data for computin...
This presentation first briefly summarizes the Bayesian dynamic multi-model integration framework with its applications, then discusses the relationship between this framework and robust AI.
This paper is concerned with multi-modal data fusion (MMDF) under unexpected modality failures in nonlinear non-Gaussian dynamic processes. An efficient framework to tackle this problem is proposed. In particular, a notion termed modality “usefulness”, which takes a value of 1 or 0, is used for indicating whether the observation of this modality is...
AI has surpassed humans across a variety of tasks such as image classification, playing games (e.g., go, "Starcraft" and poker), and protein structure prediction. However, at the same time, AI is also bearing serious controversies. Many researchers argue that little substantial progress has been made for AI in recent decades. In this paper, the aut...
In this paper, we consider sequential online prediction (SOP) for streaming data in the presence of outliers and change points. We propose an INstant TEmporal structure Learning (INTEL) algorithm to address this problem. Our INTEL algorithm is developed based on a full consideration of the duality between online prediction and anomaly detection. We...
In this paper, we are concerned with trust modeling for agents in networked computing systems. As trust is a subjective notion that is invisible, implicit and uncertain in nature, many attempts have been made to model trust with aid of Bayesian probability theory, while the field lacks a global comprehensive analysis for variants of Bayesian trust...
This paper is concerned with sequential filtering based stochastic optimization (FSO) approaches that leverage a probabilistic perspective to implement the incremental proximity method (IPM). The present FSO methods are derived based on the Kalman filter (KF) and the extended KF (EKF). In contrast with typical methods such as stochastic gradient de...
As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor nodes to the cloud server before data fusion. Such an application mode of data fusion inherits disturbing concerns...
Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationary property due to abrupt noises and neuroplastic changes in brain activities during motor control. Current state-of-the-art neural signal decoders such as Kalman filter a...
This paper is concerned with sequential state filtering in the presence of nonlinearity, non-Gaussianity and model uncertainty. For this problem, the Bayesian model averaged particle filter (BMAPF) is perhaps one of the most efficient solutions. Major advances of BMAPF have been made, while it still lacks a generic and practical approach to design...
As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor nodes to the cloud server before data fusion. Such an application mode of data fusion inherits disturbing concerns...
In this paper, we consider sequential online prediction (SOP) for streaming data in the presence of outliers and change points. We propose an INstant TEmporal structure Learning (INTEL) algorithm to address this problem. Our INTEL algorithm is developed based on a full consideration of the duality between online prediction and anomaly detection. We...
This paper studies how relationships form in heterogeneous information networks (HINs). The objective is not only to predict relationships in a given HIN more accurately but also to discover the interdependency between different type of relationships. A new relationship prediction method MULRP based on multilabel learning (MLL in brief) is proposed...
Bayesian optimization (BO) is a powerful paradigm for derivative-free global optimization of a black-box objective function (BOF) that is expensive to evaluate. However, the overhead of BO can still be prohibitive for problems with highly expensive function evaluations. In this paper, we investigate how to reduce the required number of function eva...
This contribution presents a very brief and critical discussion on automated machine learning (AutoML), which is categorized here into two classes, referred to as narrow AutoML and generalized AutoML, respectively. The conclusions yielded from this discussion can be summarized as follows: (1) most existent research on AutoML belongs to the class of...
This paper is concerned with the online estimation of a nonlinear dynamic system from a series of noisy measurements. The focus is on cases wherein outliers are present in-between normal noises. We assume that the outliers follow an unknown generating mechanism which deviates from that of normal noises, and then model the outliers using a Bayesian...
This paper is concerned with a recently developed paradigm for population-based optimization, termed particle filter optimization (PFO). This paradigm is attractive in terms of coherence in theory and easiness in mathematical analysis and interpretation. Current PFO algorithms only work for single-objective optimization cases, while many real-life...
The problem of multiple testing arises in many contexts, including testing for pairwise interaction among a large number of neurons. Recently a method was developed to control false positives when covariate information, such as distances between pairs of neurons, is available. This method, however, relies on computationally-intensive Markov Chain M...
This paper is concerned with sequential filtering based stochastic optimization (FSO) approaches that leverage a probabilistic perspective to implement the incremental proximity method (IPM).
The present FSO methods are derived based on the Kalman filter (KF) and the extended KF (EKF). In contrast with typical methods such as stochastic gradient de...
In this paper, we are concerned with trust modeling for agents in networked computing systems. As trust is a subjective notion that is
invisible, implicit and uncertain in nature, many attempts have been made to model trust with aid of Bayesian probability theory, while the field lacks a global comprehensive analysis for variants of Bayesian trust...
The growth of Internet commerce has stimulated the use of collaborative filtering (CF) algorithms as recommender systems. A CF algorithm recommends items of interest to the target user by leveraging the votes given by other similar users. In a standard CF framework, it is assumed that the credibility of every voting user is exactly the same with re...
This paper is concerned with dynamic system state estimation based on a series of noisy measurement with the presence of outliers. An incremental learning assisted particle filtering (ILAPF) method is presented, which can learn the value range of outliers incrementally during the process of particle filtering. The learned range of outliers is then...
As a derivative-free optimization method, the estimation of distribution algorithm (EDA) usually leverages a Gaussian or a Gaussian mixture model to represent the distribution of promising solutions that have been found so far. This paper investigates the application of an alternative model, namely the heavier-tailed Student's t distribution, to im...
![The yielded annealing temperature λ\documentclass[12pt]{minimal}...](profile/Bin-Liu-120/publication/282357223/figure/fig3/AS:961766276222991@1606314357355/The-yielded-annealing-temperature-ldocumentclass12ptminimal-usepackageamsmath_Q320.jpg)
We propose a global optimization algorithm based on the Sequential Monte Carlo (SMC) sampling framework. In this framework, the objective function is normalized to be a probabilistic density function (pdf), based on which a sequence of annealed target pdfs is designed to asymptotically converge on the set of global optima. A sequential importance s...
This paper studies relation prediction in heterogeneous information networks under PU learning context. One of the challenges of this problem is the imbalance of data number between the positive set P (the set of node pairs with the target relation) and the unlabeled set U (the set of node pairs without the target relation). We propose a K-means an...
This paper addresses maximum likelihood (ML) estimation based model fitting in the context of extrasolar planet detection. This problem is featured by the following properties: 1) the candidate models under consideration are highly nonlinear; 2) the likelihood surface has a huge number of peaks; 3) the parameter space ranges in size from a few to d...
This paper studies the problem of link prediction in heterogeneous information networks. Our goal is not only to predict links more accurately but also to provide more viable paths to facilitate the formation of links. A new relationship prediction method based on multi-label learning named ML3P is proposed. In ML3P, each meta-path between nodes is...
In this paper we propose a state space modeling approach for trust evaluation in wireless sensor networks. In our state space trust model (SSTM), each sensor node is associated with a trust metric, which measures to what extent the data transmitted from this node would better be trusted by the server node. Given the SSTM, we translate the trust eva...
This paper proposes a Bayesian modeling approach to address the problem of online fault-tolerant dynamic event region detection in wireless sensor networks. In our model every network node is associated with a virtual community and a trust index, which quantitatively measures the trustworthiness of this node in its community. If a sensor node's tru...
In this paper, we describe work in progress towards a real-time vision-based traffic flow prediction (TFP) system. The proposed method consists of three elemental operators, that are dynamic texture model based motion segmentation, feature extraction and Gaussian process (GP) regression. The objective of motion segmentation is to recognize the targ...
The problem of large scale multiple testing arises in many contexts, including testing for pairwise interaction among large numbers of neurons. With advances in technologies, it has become common to record from hundreds of neurons simultaneously, and this number is growing quickly, so that the number of pairwise tests can be very large. It is impor...
In this paper, we are concerned with a branch of evolutionary algorithms termed estimation of distribution (EDA), which has been successfully used to tackle derivative-free global optimization problems. For existent EDA algorithms, it is a common practice to use a Gaussian distribution or a mixture of Gaussian components to represent the statistica...
In this article, we are concerned with tracking an object of interest in video stream. We propose an algorithm that is robust against occlusion, the presence of confusing colors, abrupt changes in the object feature space and changes in object size. We develop the algorithm within a Bayesian modeling framework. The state space model is used for cap...
This paper discusses the relationship between data science and population-based algorithms, which include swarm intelligence and evolutionary algorithms. We reviewed two categories of literature, which include population-based algorithms solving data analysis problem and utilizing data analysis methods in population-based algorithms. With the expon...
In this paper, we provide a brief introduction to particle filter optimization (PFO). The particle filter (PF) theory has revolutionized probabilistic state filtering for dynamic systems, while the PFO algorithms , which are developed within the PF framework, have not attracted enough attention from the community of optimization. The purpose of thi...
Over the past few years, big data analytics has received increasing attention in all most all scientific research fields. This paper discusses the synergies between big data and evolutionary computation (EC) algorithms, including swarm intelligence and evolutionary algorithms. We will discuss the combination of big data analytics and EC algorithms,...
Cloud computing brings efficiency improvement on resource utilization nd other benefits such as on-demand service provisioning, location independence and biquitous access, elastic resource pooling, pay as usage pricing mode, etc. However, t also introduces new security issues because the data management and ownership re separated, and the managemen...
In this paper, we address the problem of detecting relatively small targets in the presence of Gaussian disturbance with unknown covariance matrix. To this end, we jointly exploit the spillover of target energy to consecutive range samples and the particular persymmetric structure of the disturbance covariance matrix to
improve the performances of...
The problem of situational awareness (SAW) is investigated from the probabilistic modeling point of view. Taking the situation as a hidden variable,
we introduce a hidden Markov model (HMM) and an extended state space model (ESSM) to mathematically express the dynamic evolution law of the
situation and the relationships between the situation and th...
A robust algorithm solution is proposed for tracking an object in complex
video scenes. In this solution, the bootstrap particle filter (PF) is
initialized by an object detector, which models the time-evolving background of
the video signal by an adaptive Gaussian mixture. The motion of the object is
expressed by a Markov model, which defines the s...
In this paper, a Bayesian dynamic model is proposed to evaluate the sensor nodes' credibilities online, in a paradigm of agricultural Internet of things (IoT). The purpose is to discriminate reliable and unreliable data items before further data analysis, and thus to implement reliable data analysis. The credibility of the sensor node of interest i...
In this paper, we devise a near-optimal fast multiple-input multiple-output (MIMO) detector. Our proposed approach is a parallel architecture of QRD in tandem with Markov-chain Monte-Carlo (MCMC) processing, referred to as hybrid parallel QRD-MCMC (HPQRD-MCMC). Simulation results show that for a 4 × 4 MIMO system, HPQRD-MCMC can reduce the detectio...
We are concerned with the problem of trust evaluation in the generic context of large scale open-ended systems. In such systems the truster agents have to interact with other trustee peers to achieve their goals, while the trustees may not behave as required in practice. The truster therefore has to predict the behaviors of potential trustees to id...
We describe an algorithm which can provide mixture summaries of multi-modal posterior distributions adaptively. The parameter space of the involved posteriors ranges in size from few-dimensional to dozens of dimensions. This work was motivated by an astrophysical problem called extra-solar planets (exoplanets) detection, wherein a challenging issue...
We consider the problem of rapid design of massive meta-material (MTM) micro-structures from a statistical point of view. A Bayesian nonparametric model, namely Gaussian Process (GP) mixture, is developed to generate the mapping relationship from the micro-structure’s geometric dimension to the electromagnetic response, which is approximately expre...
We consider non-linear state filtering problem in continuous-discrete systems, where the system dynamics is modeled by a stochastic differential equation, and noisy measurements of the system are obtained at discrete time instances. A novel particle method is proposed based on sequential importance sampling. This approach uses a bank of the continu...
We present an automated computation system for large scale design of metamaterials (MTMs). A computer model emulation (CME) technique is used to generate a forward mapping from the MTM particle’s geometric dimension to the corresponding electromagnetic (EM) response. Then the design problem translates to be a reverse engineering process which aims...
The tracking initiation problem is examined in the context of autonomous bearings-only-tracking (BOT) of a single appearing/disappearing target in the presence of clutter measurements. In general, this problem suffers from a combinatorial explosion in the number of potential tracks resulted from the uncertainty in the linkage between the target and...
In this paper, a general algorithm scheme which mixes computational intelligence with Bayesian simulation is proposed. This hybridization retains the advantage of computational intelligence in searching optimal point and the ability of Bayesian simulation in drawing random samples from any arbitrary probability density. An adaptive importance sampl...
This paper proposed a service discovery architecture (SDA) that can be applied in cloud computing environments. This architecture supports common service discovery capabilities to achieve cloud service discovery function in cloud computing environments. The main idea is that, cloud services can be divided into different cloud service domains (CSD)...
This paper deals with the problem of adaptive signal detection in the presence of Gaussian disturbance with unknown covariance matrix. A new two-stage Rao test detector is proposed, which is obtained by cascading a GLRT-based subspace detector (SD) and the Rao test. The statistical characterization for the proposed two-stage test statistic is provi...
We describe work in progress by a collaboration of astronomers and statisticians developing a suite of Bayesian data analysis tools for extrasolar planet (exoplanet) detection, planetary orbit estimation, and adaptive scheduling of observations. Our work addresses analysis of stellar reflex motion data, where a planet is detected by observing the "...
We consider a state-space modeling approach for online estimation of a signal's instantaneous frequency (IF). We take into account the general case wherein the IF may vary over time irregularly and, therefore, given several plausible models, there is uncertainty which is the best model to use. We address this dynamical model uncertainty problem usi...
For multi-target tracking (MTT) in the presence of clutters, both issues of state estimation and data association are crucial. This study tackles them jointly by Sequential Monte Carlo methods, a.k.a. particle filters. A number of novel particle algorithms are devised. The first one, which we term Monte-Carlo data association (MCDA), is a direct ex...
The purpose of this paper is threefold. First, it briefly introduces basic Bayesian techniques with emphasis on present applications in sensor networks. Second, it reviews modern Bayesian simulation methods, thereby providing an introduction to the main building blocks of the advanced Markov chain Monte Carlo and Sequential Monte Carlo methods. Las...
We consider the problem of adaptive signal detection in the presence of Gaussian noise with unknown covariance matrix. We propose a parametric radar detector by introducing a design parameter to trade off the target sensitivity with sidelobes energy rejection. The resulting detector merges the statistics of Kelly's GLRT and of the Rao test and so c...
A new type of distributed CFAR scheme (distributed fuzzy UMVE) based on fuzzy logic and Unbiased Minimum-Variance Estimation (UMVE) algorithm was proposed. In this scheme, each UMVE-CFAR detector computed the membership function value mapping to the false alarm space from the samples of reference cells, and transmitted it to the fusion center. Thes...
We discuss blending sensor scheduling strategies with particle filtering (PF) methods to deal with the problem of tracking a 'smart' target, that is, a target being able to be aware it is being tracked and act in a manner that makes the future track more difficult. We concern here how to accurately track the target with a care on concealing the obs...
This paper addresses the problem of tracking a ldquosmartrdquo target, wherein the issue of the observerpsilas concealment against the target should be taken into account, as a smart target is able to detect when it is under surveillance and react in a manner that makes future surveillance more difficult. This work proposes a sensor scheduling stra...
In this paper, we propose a novel particle filter (PF), which uses a bank of singular-value-decomposition based sampling Kalman filters (SVDSKF) to obtain the importance proposal distribution. This proposal has two properties. Firstly, it allows the particle filter to incorporate the latest observations into a prior updating routine and, secondly i...
This paper investigates a robust method for extracting frequency online from a noisy sinusoidal signal. A nearly constant frequency (NCF) model, which is adapted from the target tracking discipline, is presented to describe the evolution of the time varying frequency. A particular particle filtering algorithm, called bootstrap filter, is improved w...
The problem of active tracking for a unitary target base d on a p latform o f high-peed autonomous underwater vehicles (AUV), was researched．A robust Unscented Kalman Filter (UKF) based tracking algorithm was founded．In case of strong observation noises and long sampling intervals, it led to estimate for the state parameters, which were used to des...
In this paper, we propose a nonlinear filtering algorithm for the problem of online estimation with reasonable computing burdens. This method makes the best of the information available in process of the online estimation. Firstly, a parameter, namely estimate accuracy threshold, is defined whose value depends on the covariance matrix of the curren...
Questions
Questions (6)
In another word, what are the main obstacles for us to further learn/understand how the human brain works ?
It's reported that the proposed method facilitated the search for AF447. It's natural to think of the lost MH370, which has not been found so far.
To test an algorithm under development, I need such kind of a data set as follows. Denote \theta the parameter and y the data vector. The data elements of y, y_i, i=1,2,... , arrive one by one. The posterior p(\theta | y_1,y_2,...y_i) is expected to change along with the arrival of new data elements. For example, the posterior p(\theta | y_1,y_2,...y_i) has one peaky mode, then when y_{i+1} arrives, the posterior p(\theta | y_1,y_2,...y_i,y_{i+1}) becomes to have two or more modes. A real data case is much more preferable, while a way to simulate such a data set is also advisable.
Large IT companies like Google, facebook, Microsoft, Baidu all have their facilities and massive data supporting commensurate research on big data analysis, while for individual researchers without aforementioned support, how to do related and valuable research on big data? Surely simulation is a way, is there any other smarter way?
Bayesian methods have been a popular technique for developing artificial intelligence, e.g., Nate Silver claimed a success of utilization of Bayesian methods in predicting the US election. I wonder if Bayesian has the real potential to challenge the real human intelligence. Is there any other counterpart philosophy which is more probable to be able to challenge the real human intelligence?
