检索结果-内蒙古大学图书馆

Adaptive decoding for Brain-Machine Interfaces Through Bayesian Parameter Updates

NEURAL COMPUTATION 2011年第12期23卷 3162-3204页

作者： Li, Zheng O'Doherty, Joseph E. Lebedev, Mikhail A. Nicolelis, Miguel A. L. Duke Univ Dept Neurobiol Durham NC 27710 USA Duke Univ Ctr Neuroengn Durham NC 27710 USA Duke Univ Dept Biomed Engn Durham NC 27710 USA Duke Univ Dept Psychol & Neurosci Durham NC 27710 USA Edmond & Lily Safra Int Inst Neurosci Natal BR-59066060 Natal RN Brazil

Brain-machine interfaces (BMIs) transform the activity of neurons recorded in motor areas of the brain into movements of external actuators. Representation of movements by neuronal populations varies over time, during both voluntary limb movements and movements controlled through BMIs, due to motor learning, neuronal plasticity, and instability in recordings. To ensure accurate BMI performance over long time spans, BMI decoders must adapt to these changes. We propose the Bayesian regression self-training method for updating the parameters of an unscented Kalman filter decoder. This novel paradigm uses the decoder's output to periodically update its neuronal tuning model in a Bayesian linear regression. We use two previously known statistical formulations of Bayesian linear regression: a joint formulation, which allows fast and exact inference, and a factorized formulation, which allows the addition and temporary omission of neurons from updates but requires approximate variational inference. To evaluate these methods, we performed offline reconstructions and closed-loop experiments with rhesus monkeys implanted cortically with microwire electrodes. Offline reconstructions used data recorded in areas M1, S1, PMd, SMA, and PP of three monkeys while they controlled a cursor using a handheld joystick. The Bayesian regression self-training updates significantly improved the accuracy of offline reconstructions compared to the same decoder without updates. We performed 11 sessions of real-time, closed-loop experiments with a monkey implanted in areas M1 and S1. These sessions spanned 29 days. The monkey controlled the cursor using the decoder with and without updates. The updates maintained control accuracy and did not require information about monkey hand movements, assumptions about desired movements, or knowledge of the intended movement goals as training signals. These results indicate that Bayesian regression self-training can maintain BMI control accuracy over long p

关键词： BRAIN-computer interfaces decoding algorithms MOTOR neurons ACTUATORS BAYESIAN analysis REGRESSION analysis

来源：评论

学校读者我要写书评

暂无评论

System combination by driven decoding

System combination by driven decoding

引用

32nd IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Lecouteux, B. Linares, G. Esteve, Y. Mauclair, J. Univ Avignon LIA Avignon France Univ Maine LIUM Le Mans France

ISBN: (纸本)1424407281

The combination of Automatic Speech Recognition (ASR) systems generally relies on a posteriori merge of system outputs or on a cross-adaptation. In this paper, we propose an integrated approach where the search of a primary system is driven by the outputs of a secondary one. This method allows to drive the primary system search by using the one-best hypotheses and the word posteriors gathered from the secondary system. Experiments are carried out within the experimental framework of the ESTER evaluation campaign [1]. Results show that the driven decoding algorithm significantly outperforms the two single ASR systems (-8% of relative WER, -1.7% absolute). Finally, we investigate the interactions between driven decoding and cross-adaptations. The best cross-adaptation strategy in combination with the driven decoding process brings to a final absolute gain of about 1.9% WER.

关键词： system combination decoding algorithms broadcast news transcription confidence measures

来源：评论

学校读者我要写书评

暂无评论

Modified Log-MAP Algorithm for Simplified decoding of Turbo and Turbo TCM Codes

Modified Log-MAP Algorithm for Simplified Decoding of Turbo ...

引用

69th IEEE Vehicular Technology Conference

作者： Papaharalabos, Stylianos Sybis, Michal Tyczka, Piotr Mathiopoulos, P. Takis Natl Observ Athens ISARS Palea Penteli 15236 Greece Poznan Univ Tech Chair Wireless Commun PL-60965 Poznan Poland

ISBN: (纸本)9781424425167

A novel method for approximating the optimal max(star) operator in Log-MAP decoding of turbo and turbo trellis-coded modulation (TTCM) codes is presented. The max(star) operation is performed on n>2 rather than on only two inputs, as it is in the conventional approach. The approximation uses a very simple max operation and a look-up table (LUT) with only eight stored values. Complexity comparison reveals a significant reduction in the number of operations required per decoding step for the presented approximation, as compared with the conventional Log-MAP decoding. Performance evaluation results are presented for both turbo and TTCM codes, showing the near-optimal performance of the novel approach.

关键词： turbo codes turbo trellis-coded modulation decoding algorithms

来源：评论

学校读者我要写书评

暂无评论

On the complexity of some cryptographic problems based on the general decoding problem

On the complexity of some cryptographic problems based on th...

引用

IEEE International Symposium on Information Theory

作者： Johansson, T Jönsson, F Lund Univ Dept Informat Technol S-22100 Lund Sweden

ISBN: (纸本)0780350006

A new probabilistic algorithm for decoding one received word from a set of many given received words, into a codeword such that the Hamming distance between the received word and the codeword is at most t, is proposed. The new algorithm is applicable to several cryptographic problems, such as the Stern identification scheme, the McEliece public-key cryptosystem, and in correlation attacks on stream ciphers. When applicable, it runs significantly faster than previous algorithms used for attacks on these cryptosystems.

关键词： complexity correlation attack decoding algorithms McEliece cryptosystem Stern identification system

来源：评论

学校读者我要写书评

暂无评论

E2E Segmenter: Joint Segmenting and decoding for Long-Form ASR 23

E2E Segmenter: Joint Segmenting and Decoding for Long-Form A...

引用

Interspeech Conference

作者： Huang, W. Ronny Chang, Shuo-yiin Rybach, David Prabhavalkar, Rohit Sainath, Tara N. Allauzen, Cyril Peyser, Cal Lu, Zhiyun Google Res Mountain View CA 94043 USA

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice activity detector (VAD) that decides segment boundary locations based purely on acoustic speech/non-speech information. VAD segmenters, however, may be sub-optimal for real-world speech where, e.g., a complete sentence that should be taken as a whole may contain hesitations in the middle ("set an alarm for... 5 o'clock"). We propose to replace the VAD with an end-to-end ASR model capable of predicting segment boundaries in a streaming fashion, allowing the segmentation decision to be conditioned not only on better acoustic features but also on semantic features from the decoded text with negligible extra computation. In experiments on real world long-form audio (YouTube) with lengths of up to 30 minutes long, we demonstrate 8.5% relative WER improvement and 250 ms reduction in median end-of-segment latency compared to the VAD baseline on a state-of-the-art Conformer RNN-T model.

关键词： speech recognition speech segmentation decoding algorithms beam search

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Exponential Min Sum decoding Algorithm 6

An Adaptive Exponential Min Sum Decoding Algorithm

引用

6th Conference on Cloud and Internet of Things (CIoT)

作者： Zhang Weijia Jayakody, Dushantha Nalin K. Tomsk Polytech Univ Sch Comp Sci & Robot Tomsk Russia Lusofona Univ COPELABS P-1700097 Lisbon Portugal

ISBN: (纸本)9798350396690

The belief propagation (BP) algorithm for low density parity check (LDPC) codes has proven to have excellent performance and is close to the Shannon limit. However, the high computational complexity is not conducive to realistic use. Although the min sum algorithm (MSA) improves the computational convenience and applicability. It also weakens its decoding capability. In order to improve the decoding performance of MSA and exploit the potential, this paper propose an adaptive exponential correction factor. This can improve the decoding performance of MSA. Adaptive exponential min sum algorithm (AEMSA) demonstrate a noticeable improvement over the normalized min sum algorithm (NMSA) and the BP algorithm in high signal to noise ratio (SNR). AEMSA is also a simple, efficient, low power consuming and highly potential decoding algorithm that can be applied in hardware implementations.

关键词： LDPC Codes decoding algorithms Min Sum Adaptive Exponential Internet of Things (IoTs)

来源：评论

学校读者我要写书评

暂无评论

WiMAX Physical Layer Optimization by Implementing SOVA decoding Algorithm

WiMAX Physical Layer Optimization by Implementing SOVA Decod...

引用

International Conference on Circuits, Systems, Communication and Information Technology Applications (CSCITA)

作者： Kene, Jagdish D. Kulat, Kishor D. Visvesvaraya Natl Inst Technol Nagpur Maharashtra India

ISBN: (纸本)9781479924943

Turbo code provides relatively better performance as compare to convolution codes at lower Signal to Noise Ratio. Turbo code offers an outstanding coding gain very close to Shannon limit over an AWGN channel to achieve maximum throughput particularly for WiMAX application. The objective of this paper is to Study the Mobile WiMAX system performance by implementing the turbo codes using Soft Output Viterbi Algorithm (SOVA). Turbo decoder is optimized by modifying the SOVA that contributed to the system performance optimization. For different transmission conditions, BER performance has been simulated and compared to the conventional Log-MAP decoding algorithm. The performance of mobile WiMAX system has also been tested for the effect of various decoding algorithms, Frame size and Code rates.

关键词： decoding algorithms FEC codes SISO Shannon limit Viterbi algorithm WiMAX

来源：评论

学校读者我要写书评

暂无评论

Key Reduction of McEliece's Cryptosystem Using List decoding

Key Reduction of McEliece's Cryptosystem Using List Decoding

引用

IEEE International Symposium on Information Theory (ISIT)

作者： Barbier, Morgan Barreto, Paulo S. L. M. Computer Science Laboratory of École Polytechnique LIX INRIA Saclay Île France Department of Computer and Digital Systems Engineering Escola Politécnica University of São Paulo Brazil

ISBN: (纸本)9781457705953

Different variants of the code-based McEliece cryptosystem were proposed to reduce the size of the public key. All these variants use very structured codes, which open the door to new attacks exploiting the underlying structure. In this paper, we show that the quasi-dyadic variant can be designed to resist all known attacks. In light of a new study on list decoding algorithms for binary Goppa codes, we explain, as already suggested by Bernstein, Lange and Peters, how to increase the security level for given public keysizes. Using the state-of-the-art list decoding algorithm instead of unique decoding, we exhibit a keysize gain of about 4% for the standard McEliece cryptosystem and up to 21% for the adjusted quasi-dyadic variant.

关键词： Computer science decoding Goppa codes Polynomials Public key binary Goppa codes binary codes code-based McEliece cryptosystem decoding decoding algorithms public key cryptography public key size rduction quasidyadic variant security level state-of-the-art list decoding algorithm

来源：评论

学校读者我要写书评

暂无评论

Simplified Log-MAP decoding with max* Approximation Based on the Jensen Inequality

Simplified Log-MAP Decoding with <i>max</i>* Approximation B...

引用

21st Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Sybis, Michal Tyczka, Piotr Papaharalabos, Stylianos Mathiopoulos, Panayiotis Takis Poznan Univ Tech Chair Wireless Commun Poznan Poland Natl Observ Athens Inst Space Applicat & Remote Sensing Athens Greece

ISBN: (纸本)9781424480166

In the paper, a modified Log-MAP algorithm based on a novel approximation of the max* operator derived from the Jensen inequality is proposed. In this approach, the max* operation is performed on n >= 2 arguments, thus the recursive calculations are avoided and significant reduction in the number of operations performed per decoding step, as compared with the conventional Log-MAP, is achieved. Simulation results of BER performance for both turbo codes and turbo trellis-coded modulation (TTCM) employing the new algorithm are given, showing the near-optimal performance of the proposed algorithm.

关键词： decoding algorithms Log-MAP algorithm Turbo codes Turbo TCM max* operator reduced-complexity algorithms

来源：评论

学校读者我要写书评

暂无评论

The Highest Expected Reward decoding for HMMs with Application to Recombination Detection

The Highest Expected Reward Decoding for HMMs with Applicati...

引用

21st Annual Symposium on Combinatorial Pattern Matching

作者： Nanasi, Michal Vinar, Tomas Brejova, Brona Comenius Univ Fac Math Phys & Informat Bratislava 84248 Slovakia

ISBN: (纸本)9783642135088

Hidden Markov models are traditionally decoded by the Viterbi algorithm which finds the highest probability state path in the model. In recent years, several limitations of the Viterbi decoding have been demonstrated, and new algorithms have been developed to address them (Kall et al., 2005;Brejova et al., 2007;Gross et al., 2007;Brown and Truszkowski, 2010). In this paper, we propose a new efficient highest expected reward decoding algorithm (HERD) that allows for uncertainty in boundaries of individual sequence features. We demonstrate usefulness of our approach on jumping HMMs for recombination detection in viral genomes.

关键词： hidden Markov models decoding algorithms recombination detection jumping HMMs

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：