Author name cluster

Xiaodong Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

21 papers

2 author rows

EAAI Journal 2026 Journal Article

Analog circuit test point selection method for fault diagnosis based on deep reinforcement learning

Haochi Yang
Xiaodong Liu
Tianyu Gao
Jingli Yang

Reliable operation of analog circuits is fundamental to the safety of medical instruments, automotive controllers, and aerospace systems. A prerequisite for effective fault diagnosis is the selection of a compact yet informative set of test nodes, commonly referred to as analog test-point selection (ATPS). Existing optimization- and search-based approaches often exhibit slow convergence and susceptibility to sub-optimal solutions when applied to large-scale circuits. In this study, ATPS is reformulated as a sequential decision-making problem addressed by a Dual-Stream Dueling Deep-Q Network (DS-DDQN). The framework is designed to learn, from simulation data, the most valuable next test node under a user-defined cost constraint. Two types of input are processed: the evolving diagnostic state, representing unresolved fault groups, and the available cost budget. To achieve scalability, raw simulation responses are compressed into compact fault-isolation scores through a Gaussian mixture model, allowing efficient learning even in the presence of extensive fault dictionaries. Experimental evaluations on industry-standard benchmarks and real-world circuits demonstrate improvements in diagnostic accuracy from 3. 94% to 33. 72% and reductions in selection time by nearly an order of magnitude, compared with circuit-level outputs and representative baseline methods.

Details DOI

EAAI Journal 2025 Journal Article

From smoke to fire: A forest fire early warning and risk assessment model fusing multimodal data

Peixian Jin
Pengle Cheng
Xiaodong Liu
Ying Huang

Experienced forest firefighters can integrate knowledge of smoke patterns and risk factors to assess fire risk and anticipate potential fire spread and outbreaks in complex, variable environments. This study simulates the previously mentioned monitoring process and presents the Multimodal Smoke Risk Estimation Network (MM-SRENet), an innovative multimodal fusion model. This model uniquely integrates the Multi-Scale Dilation Block and Repulsion Loss into a lightweight and efficient target detection system to accurately identify smoke's presence. Furthermore, an advanced backbone based on star operation extracts the scene characteristics associated with smoke and merges them with various fire risk factors. The objective is to simulate fire risk assessments in smoke scenarios and to reduce the misallocation of fire resources resulting from false alarms and missed alerts. The proposed model was trained and validated on a multimodal dataset comprising multiple backgrounds. It successfully identified smoke features and fire potential risks in different scenarios, achieving a prediction accuracy of 93. 06 %. Fusing smoke images with fire risk data resulted in an 18. 75 % improvement in recognition accuracy compared to the single modal model. This work bridges the gap between multimodal data fusion and forest fire risk monitoring, providing a new direction for future intelligent forest fire prevention and control practices.

Details DOI

EAAI Journal 2025 Journal Article

Global-local coupled learning method for autonomous underwater vehicle side-scan sonar image recognition

Fei Yu
Xiaodong Liu
Wei Liu
Jixin Liu

Independent real-time recognition of deep-sea targets is still challenging for autonomous underwater vehicles. The side-scan sonar plays an essential role in the fields of marine bottom topographic survey and resource exploration. For the deep and distant seas that are inaccessible to humankind, the traditional methods mainly collect information first and then manually recognize it offline, which has the shortcomings of weak recognition robustness and insufficient real-time. Unlike the previous methods, a global-local coupled learning method based on side-scan sonar image recognition is proposed, which can assist in independently exploring deep-sea targets. Firstly, global recognition is performed to extract the image texture information using the deep learning-based segmentation network module and initially recognize the marine target species. Secondly, local recognition is performed, and the deep learning-based local attention module is used to optimize global recognition and refine image types. Finally, the results of the previous two steps are fused using the confidence screening strategy to output the final recognition results. The coupled learning method is compared with other classical and lightweight methods based on the side-scan sonar datasets. Simulation experiments demonstrate that the proposed method is robust and real-time, which can be widely used in marine target recognition.

Details DOI

TAAS Journal 2025 Journal Article

GSFL: A Privacy-Preserving Grouping-Split Federated Learning Approach in Resource-Constrained Edge Computing Scenarios

Qi Liu
Zhilu Wang
Xiaokang Zhou
Yonghong Zhang
Xiaodong Liu
Haiyang Lin

The advancement of mobile multimedia communications, 5G, and Internet of Things (IoT) has led to the widespread use of edge devices, including sensors, smartphones, and wearables. This has generated in a large amount of distributed data, leading to new prospects for deep learning. However, this data is confined within data silos and contains sensitive information, making it difficult to be processed in a centralized manner, particularly under stringent data privacy regulations. Federated learning (FL) offers a solution by enabling collaborative learning while ensuring privacy. Nonetheless, data and device heterogeneity complicate FL implementation. This research presents a specialized FL algorithm for heterogeneous edge computing. It integrates a lightweight grouping strategy for homogeneous devices, a scheduling algorithm within groups, and a Split Learning (SL) approach. These contributions enhance model accuracy and training speed, alleviate the burden on resource-constrained devices, and strengthen privacy. Experimental results demonstrate that the GSFL outperforms FedAvg and SplitFed by 6.53× and 1.18×. Under experimental conditions with $\alpha=0.05$, representing a highly heterogeneous data distribution typical of extreme Non-IID scenarios, GSFL showed better accuracy compared to FedAvg by 10.64%, HACCS by 4.53%, and Cluster-HSFL by 1.16%. GSFL effectively balances privacy protection and computational efficiency for real-world applications in mobile multimedia communications.

Details DOI

IJCAI Conference 2025 Conference Paper

ProMEA: Prompt-driven Expansion and Alignment for Single Domain Generalization

Yunyun Wang
Yi Guo
Xiaodong Liu
Songcan Chen

In single Domain Generalization (single-DG), data scarcity in the single source domain hampers the learning for invariant features, leading to overfitting over source domain and poor generalization to unseen target domains. Existing single-DG methods primarily augment the source domain by adversarial generation. However, there are still two key challenges. i) With simple feature perturbation to confuse the classifier, it may generate unnatural samples with semantic ambiguity or distortion. ii) It is still difficult to cover the sufficient shift in a real domain by generating indistinguishable samples from source data, thus the learning model is inescapable from overfitting to the single source domain. To this end, we turn to augment the domain prompt, considering that text prompt perturbation is easier to generate and generalize. Then the source domain is expanded with the guidance of augmented text prompts, which are learnable with both semantic consistency and style diversity. Specifically, we propose a ProMpt-driven Expansion and Alignment (ProMEA) method for single-DG, in which a Domain Prompt Expansion module is first developed to expand the single source domain with frequency features of augmented text prompts, in which the amplitude spectrum predominantly harbors the domain style information. With source prompts, a Domain Prompt Alignment module is further designed in inference for adapting target samples to the expanded source domains, in order to reduce the domain discrepancy. Finally, empirically results over single-DG benchmarks demonstrate the superiority of our proposal.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SAS: Simulated Attention Score

Chuanyang Zheng
Jiankai Sun
Yihang Gao
Yuehao Wang
Peihao Wang
Jing Xiong
Liliang Ren
Hao Cheng

The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We further analyze the MHA and observe that its performance improves as the number of attention heads increases, provided the hidden size per head remains sufficiently large. Therefore, increasing both the head count and hidden size per head with minimal parameter overhead can lead to significant performance gains at a low cost. Motivated by this insight, we introduce Simulated Attention Score (SAS), which maintains a compact model size while simulating a larger number of attention heads and hidden feature dimension per head. This is achieved by projecting a low-dimensional head representation into a higher-dimensional space, effectively increasing attention capacity without increasing parameter count. Beyond the head representations, we further extend the simulation approach to feature dimension of the key and query embeddings, enhancing expressiveness by mimicking the behavior of a larger model while preserving the original model size. To control the parameter cost, we also propose Parameter-Efficient Attention Aggregation (PEAA). Comprehensive experiments on a variety of datasets and tasks demonstrate the effectiveness of the proposed SAS method, achieving significant improvements over different attention variants.

PDF Details

AAAI Conference 2025 Conference Paper

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering

Xiaopeng Li
Shasha Li
Shezheng Song
Huijun Liu
Bin Ji
Xi Wang
Jun Ma
Jie Yu

The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for efficiently updating a small amount of knowledge of LLMs and has attracted much attention. In particular, local editing methods, which directly update model parameters, are proven suitable for updating small amounts of knowledge. Local editing methods update weights by computing least squares closed-form solutions and identify edited knowledge by vector-level matching in inference, which achieve promising results. However, these methods still require a lot of time and resources to complete the computation. Moreover, vector-level matching lacks reliability, and such updates disrupt the original organization of the model's parameters. To address these issues, we propose a detachable and expandable Subject Word Embedding Altering (SWEA) framework, which finds the editing embeddings through token-level matching and adds them to the subject word embeddings in Transformer input. To get these editing embeddings, we propose optimizing then suppressing fusion method, which first optimizes learnable embedding vectors for the editing target and then suppresses the Knowledge Embedding Dimensions (KEDs) to obtain final editing embeddings. We thus propose SWEAOS method for editing factual knowledge in LLMs. We demonstrate the overall state-of-the-art (SOTA) performance of SWEAOS on the CounterFact and zsRE datasets. To further validate the reasoning ability of SWEAOS in editing knowledge, we evaluate it on the more complex RippleEdits benchmark. The results demonstrate that SWEAOS possesses SOTA reasoning ability.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Towards Verifiable Text Generation with Generative Agent

Bin Ji
Huijun Liu
Mingzhe Du
Shasha Li
Xiaodong Liu
Jun Ma
Jie Yu
See-Kiong Ng

Text generation with citations makes it easy to verify the factuality of Large Language Models’ (LLMs) generations. Existing one-step generation studies expose distinct shortages in answer refinement and in-context demonstration matching. In light of these challenges, we propose R2-MGA, a Retrieval and Reflection Memory-augmented Generative Agent. Specifically, it first retrieves the memory bank to obtain the best-matched memory snippet, then reflects the retrieved snippet as a reasoning rationale, next combines the snippet and the rationale as the best-matched in-context demonstration. Additionally, it is capable of in-depth answer refinement with two specifically designed modules. We evaluate R2-MGA across five LLMs on the ALCE benchmark. The results reveal R2-MGA’ exceptional capabilities in text generation with citations. In particular, compared to the selected baselines, it delivers up to +58.8% and +154.7% relative performance gains on answer correctness and citation quality, respectively. Extensive analyses strongly support the motivations of R2-MGA.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Optimal Auction Design with User Coupons in Advertising Systems

Xiaodong Liu
Zhikang Fan
Yiming Ding
Yuan Guo
Lihua Zhang
Changcheng Li
Dongying Kong
Han Li

Online advertising is a major revenue source for most Internet companies. The advertising opportunities are usually sold to advertisers through auctions that take into account the bids of the advertisers and the click-through rates (CTRs) and the conversion rates (CVRs) of the users. Standard auction design theory perceives both the CTRs and the CVRs as constants. We consider a new auction mechanism that offers coupons to users when displaying the ads. Such coupons allow the user to buy the advertisers' products or services at a lower price, which increases both the CTRs and the CVRs of the ads. In this paper, we formulate the problem mathematically and perform a systematic analysis. We characterize the set of individually rational and incentive compatible mechanisms in our setting. Based on the characterization, we identify the optimal strategy of offering coupons that maximizes the platform's expected revenue. We also conduct extensive experiments on both synthetic data and industrial data. Our experiment results show that our mechanism significantly improves both the revenue and welfare of the platform, thereby creating a win-win situation for all parties including the platform, the advertisers, and the user.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Augmenting Language Models with Long-Term Memory

Weizhi Wang
Li Dong
Hao Cheng
Xiaodong Liu
Xifeng Yan
Jianfeng Gao
Furu Wei

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history. We design a novel decoupled network architecture with the original backbone LLM frozen as a memory encoder and an adaptive residual side-network as a memory retriever and reader. Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness. Enhanced with memory-augmented adaptation training, LongMem can thus memorize long past context and use long-term memory for language modeling. The proposed memory retrieval module can handle unlimited-length context in its memory bank to benefit various downstream tasks. Typically, LongMem can enlarge the long-form memory to 65k tokens and thus cache many-shot extra demonstration examples as long-form memory for in-context learning. Experiments show that our method outperforms strong long-context models on ChapterBreak, a challenging long-context modeling benchmark, and achieves remarkable improvements on memory-augmented in-context learning over LLMs. The results demonstrate that the proposed method is effective in helping language models to memorize and utilize long-form contents.

PDF Details

IJCAI Conference 2023 Conference Paper

Auto-bidding with Budget and ROI Constrained Buyers

Xiaodong Liu
Weiran Shen

In online advertising markets, an increasing number of advertisers are adopting auto-bidders to buy advertising slots. This tool simplifies the process of optimizing bids based on various financial constraints. In our study, we focus on second-price auctions where bidders have both private budget and private ROI (return on investment) constraints. We formulate the auto-bidding system design problem as a mathematical program and analyze the auto-bidders' bidding strategy under such constraints. We demonstrate that our design ensures truthfulness, i. e. , among all pure and mixed strategies, always reporting the truthful budget and ROI is an optimal strategy for the bidders. Although the program is non-convex, we provide a fast algorithm to compute the optimal bidding strategy for the bidders based on our analysis. We also study the welfare and provide a lower bound for the PoA (price of anarchy). Moreover, we prove that if all bidders utilize our auto-bidding system, a Bayesian Nash equilibrium exists. We provide a sufficient condition under which the iterated best response process converges to such an equilibrium. Finally, we conduct extensive experiments to empirically evaluate the effectiveness of our design.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Bridging Discrete and Backpropagation: Straight-Through and Beyond

Liyuan Liu
Chengyu Dong
Xiaodong Liu
Bin Yu
Jianfeng Gao

Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. First, we examine the widely used Straight-Through (ST) heuristic and demonstrate that it works as a first-order approximation of the gradient. Guided by our findings, we propose ReinMax, which achieves second-order accuracy by integrating Heun’s method, a second-order numerical method for solving ODEs. ReinMax does not require Hessian or other second-order derivatives, thus having negligible computation overheads. Extensive experimental results on various tasks demonstrate the superiority of ReinMax over the state of the art.

PDF Details

ICLR Conference 2023 Conference Paper

Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models

Yong Zhong
Hongtao Liu
Xiaodong Liu
Fan Bao
Weiran Shen
Chongxuan Li

Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized deep generative model (Reg-DGM), which leverages a nontransferable pre-trained model to reduce the variance of generative modeling with limited data. Formally, Reg-DGM optimizes a weighted sum of a certain divergence and the expectation of an energy function, where the divergence is between the data and the model distributions, and the energy function is defined by the pre-trained model w.r.t. the model distribution. We analyze a simple yet representative Gaussian-fitting case to demonstrate how the weighting hyperparameter trades off the bias and the variance. Theoretically, we characterize the existence and the uniqueness of the global minimum of Reg-DGM in a non-parametric setting and prove its convergence with neural networks trained by gradient-based methods. Empirically, with various pre-trained feature extractors and a data-dependent energy function, Reg-DGM consistently improves the generation performance of strong DGMs with limited data and achieves competitive results to the state-of-the-art methods. Our implementation is available at https://github.com/ML-GSAI/Reg-ADA-APA.

Details

NeurIPS Conference 2022 Conference Paper

Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Dongkuan (DK) Xu
Subhabrata Mukherjee
Xiaodong Liu
Debadeepta Dey
Wenhui Wang
Xiang Zhang
Ahmed Awadallah
Jianfeng Gao

Traditional knowledge distillation (KD) methods manually design student architectures to compress large models given pre-specified computational cost. This requires several trials to find viable students, and repeating the process with change in computational budget. We use Neural Architecture Search (NAS) to automatically distill several compressed students with variable cost from a large model. Existing NAS methods train a single SuperLM consisting of millions of subnetworks with weight-sharing, resulting in interference between subnetworks of different sizes. Additionally, many of these works are task-specific requiring task labels for SuperLM training. Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (e. g. , K=3 can generate typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e. g. , self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training. Task-agnostic training and search allow students to be reused for fine-tuning on any downstream task. Experiments on GLUE benchmark demonstrate AutoDistil to outperform state-of-the-art KD and NAS methods with upto 3x reduction in computational cost and negligible loss in task performance. Code and model checkpoints are available at https: //github. com/microsoft/autodistil.

PDF Details

IJCAI Conference 2022 Conference Paper

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention

Yichong Xu
Chenguang Zhu
Shuohang Wang
Siqi Sun
Hao Cheng
Xiaodong Liu
Jianfeng Gao
Pengcheng He

Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89. 4% in comparison to the human accuracy of 88. 9%.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

Few-Shot Learning Evaluation in Natural Language Understanding

Subhabrata Mukherjee
Xiaodong Liu
Guoqing Zheng
Saghar Hosseini
Hao Cheng
Ge Yang
Christopher Meek
Ahmed Awadallah

Most recent progress in natural language understanding (NLU) has been driven, in part, by benchmarks such as GLUE, SuperGLUE, SQuAD, etc. In fact, many NLU models have now matched or exceeded "human-level" performance on many tasks in these benchmarks. Most of these benchmarks, however, give models access to relatively large amounts of labeled data for training. As such, the models are provided far more data than required by humans to achieve strong performance. That has motivated a line of work that focuses on improving few-shot learning performance of NLU models. However, there is a lack of standardized evaluation benchmarks for few-shot NLU resulting in different experimental settings in different papers. To help accelerate this line of work, we introduce CLUES, a benchmark for evaluating the few-shot learning capabilities of NLU models. We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks. We also demonstrate differences between alternative model families and adaptation techniques in the few shot setting. Finally, we discuss several principles and choices in designing the experimental settings for evaluating the true few-shot learning performance and suggest a unified standardized approach to few-shot learning evaluation. We aim to encourage research on NLU models that can generalize to new tasks with a small number of examples. Code and data for CLUES are available at https: //github. com/microsoft/CLUES.

PDF Details

NeurIPS Conference 2021 Conference Paper

Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Ge Yang
Edward Hu
Igor Babuschkin
Szymon Sidor
Xiaodong Liu
David Farhi
Nick Ryder
Jakub Pachocki

Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization ($\mu$P), many optimal HPs remain stable even as model size changes. This leads to a new HP tuning paradigm we call *$\mu$Transfer*: parametrize the target model in $\mu$P, tune the HP indirectly on a smaller model, and *zero-shot transfer* them to the full-sized model, i. e. , without directly tuning the latter at all. We verify $\mu$Transfer on Transformer and ResNet. For example, 1) by transferring pretraining HPs from a model of 13M parameters, we outperform published numbers of BERT-large (350M parameters), with a total tuning cost equivalent to pretraining BERT-large once; 2) by transferring from 40M parameters, we outperform published numbers of the 6. 7B GPT-3 model, with tuning cost only 7% of total pretraining cost. A Pytorch implementation of our technique can be found at github. com/microsoft/mup. See arxiv. org for the full, up-to-date version of this work.

PDF Details

NeurIPS Conference 2019 Conference Paper

Unified Language Model Pre-training for Natural Language Understanding and Generation

Li Dong
Nan Yang
Wenhui Wang
Furu Wei
Xiaodong Liu
Yu Wang
Jianfeng Gao
Ming Zhou

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2. 0 and CoQA question answering tasks. Moreover, UniLM achieves new state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40. 51 (2. 04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35. 75 (0. 86 absolute improvement), the CoQA generative question answering F1 score to 82. 5 (37. 1 absolute improvement), the SQuAD question generation BLEU-4 to 22. 12 (3. 75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2. 67 (human performance is 2. 65). The code and pre-trained models are available at https: //github. com/microsoft/unilm.

PDF Details

NeurIPS Conference 2018 Conference Paper

Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models

Minjia Zhang
Wenhan Wang
Xiaodong Liu
Jianfeng Gao
Yuxiong He

Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the computational cost of the decoding process, which consists of a softmax layer over a large vocabulary. We observe that in the decoding of many NLP tasks, only the probabilities of the top-K hypotheses need to be calculated preciously and K is often much smaller than the vocabulary size. This paper proposes a novel softmax layer approximation algorithm, called Fast Graph Decoder (FGD), which quickly identifies, for a given context, a set of K words that are most likely to occur according to a NLM. We demonstrate that FGD reduces the decoding time by an order of magnitude while attaining close to the full softmax baseline accuracy on neural machine translation and language modeling tasks. We also prove the theoretical guarantee on the softmax approximation quality.

PDF Details

EAAI Journal 2015 Journal Article

Time series long-term forecasting model based on information granules and fuzzy clustering

Weina Wang
Witold Pedrycz
Xiaodong Liu

In spite of the impressive diversity of models of time series, there is still an acute need to develop constructs that are both accurate and transparent. Meanwhile, long-term time series prediction is challenging and of great interest to both practitioners and research community. The role of information granulation is to organize detailed numerical data into some meaningful, semantically sound entities. With this regard, the design of time series forecasting models used the information granulation is interpretable and easily comprehended by humans. In order to cluster information granules, a modified fuzzy c-means which does not require that data have the same dimensionality is proposed. Then, we develop forecasting model combining the modified fuzzy c-means and information granulation for solving the problem of time series long-term prediction. Synthetic time series, chaotic Mackey–Glass time series, power demand, daily temperatures, stock index, and wind speed are used in a series of experiments. The experimental results show that the proposed model produces better forecasting results than several existing models.

Details DOI

IROS Conference 2009 Conference Paper

Visual odometry for the Autonomous City Explorer

Tianguang Zhang
Xiaodong Liu
Kolja Kühnlenz
Martin Buss

The goal of the Autonomous City Explorer (ACE) is to navigate autonomously, efficiently and safely in an unpredictable and unstructured urban environment. To achieve this aim, an accurate localization is one of the preconditions. Due to the characteristics of our navigation environment, an elaborated visual odometry system is proposed to estimate the current position and orientation of the ACE platform. The existing algorithms of optical flow computation are experimentally evaluated and compared. The method based on pyramidal Lucas-Kanade algorithm with high-speed performance is selected. Based on the optical flow in 2D images, the camera ego-motion is estimated using image Jacobian matrix and least squares method. The kinematic model is set up to map the camera ego-motion to the robot motion. To eliminate systematic errors, a novel system calibration approach is proposed. Finally the odometry system is evaluated in experiments.

Details