检索结果-南通市图书馆

Journal of Computer Science & Technology 2013年第4期28卷 720-731页

作者： Concha Bielza Juan A. Fernndez del Pozo Pedro Larranaga Computational intelligence group Department of Artificial IntelligenceTechnical University of Madrid

Parameter setting for evolutionary algorithms is still an important issue in evolutionary computation. There are two main approaches to parameter setting： parameter tuning and parameter control. In this paper, we introduce self-adaptive parameter control of a genetic algorithm based on Bayesian network learning and simulation. The nodes of this Bayesian network are genetic algorithm parameters to be controlled. Its structure captures probabilistie conditional （in）dependence relationships between the parameters. They are learned from the best individuals, i.e., the best configurations of the genetic algorithm. Individuals are evaluated by running the genetic algorithm for the respective parameter configuration. Since all these runs are time-consuming tasks, each genetic algorithm uses a small-sized population and is stopped before convergence. In this way promising individuals should not be lost. Experiments with an optimal search problem for simultaneous row and column orderings yield the same optima as state-of-the-art methods but with a sharp reduction in computational time. Moreover, our approach can cope with as yet unsolved high-dimensional problems.

关键词： genetic algorithm estimation of distribution algorithm parameter control parameter setting Bayesian network

Model-based reinforcement learning for router port queue configurations

在线全文

学校读者我要写书评

暂无评论

Intelligent and Converged Networks 2021年第3期2卷 177-197页

作者： Ajay Kattepur Sushanth David Swarup Kumar Mohalik intelligence system group Ericsson ResearchBangalore 560093India Ericsson Managed Services Unit in Texas PlanoTX 75025USA

Fifth-generation(5G)systems have brought about new challenges toward ensuring Quality of Service(QoS)in differentiated *** includes low latency applications,scalable machine-to-machine communication,and enhanced mobile broadband *** order to satisfy these requirements,the concept of network slicing has been introduced to generate slices of the network with specific *** order to meet the requirements of network slices,routers and switches must be effectively configured to provide priority queue provisioning,resource contention management and *** routers from vendors,such as Ericsson,Cisco,and Juniper,have traditionally been an expert-driven process with static rules for individual flows,which are prone to sub optimal configurations with varying traffic *** this paper,we model the internal ingress and egress queues within routers via a queuing *** effects of changing queue configuration with respect to priority,weights,flow limits,and packet drops are studied in *** is used to train a model-based Reinforcement Learning(RL)algorithm to generate optimal policies for flow prioritization,fairness,and congestion *** efficacy of the RL policy output is demonstrated over scenarios involving ingress queue traffic policing,egress queue traffic shaping,and one-hop router coordinated traffic *** is evaluated over a real application use case,wherein a statically configured router proved sub optimal toward desired QoS *** automated configuration of routers and switches will be critical for multiple 5G deployments with varying flow requirements and traffic patterns.

关键词： router port queues model-based Reinforcement Learning(RL) network slicing

Oligodendroglial heterogeneity in health,disease,and recovery:deeper insights into myelin dynamics

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第11期20卷 3179-3192页

作者： Pieter-Jan Serneels Julie D.De Schutter Lies De Groef Lieve Moons Steven Bergmans KU Leuven Leuven Brain InstituteDepartment of BiologyAnimal Physiology and Neurobiology DivisionNeural Circuit Development&Regeneration Research GroupLeuvenBelgium KU Leuven Leuven Brain InstituteDepartment of BiologyAnimal Physiology and Neurobiology DivisionCellular Communication&Neurodegeneration Research GroupLeuvenBelgium

Decades of research asserted that the oligodendroglial lineage comprises two cell types:oligodendrocyte precursor cells and ***,recent studies employing single-cell RNA sequencing techniques have uncovered novel cell states,prompting a revision of the existing *** forward,the oligodendroglial lineage should be delineated into five distinct cell states:oligodendrocyte precursor cells,committed oligodendrocyte precursor cells,newly formed oligodendrocytes,myelin-forming oligodendrocytes,and mature *** new classification system enables a deeper understanding of the oligodendroglia in both physiological and pathological *** this uniform terminology will facilitate comparison and integration of data across ***,including the consolidation of findings from various demyelinating models,is essential to better understand the pathogenesis of demyelinating ***,comparing injury models across species with varying regenerative capacities can provide insights that may lead to new therapeutic strategies to overcome remyelination ***,by standardizing terminology and synthesizing data from diverse studies across different animal models,we can enhance our understanding of myelin pathology in central nervous system disorders such as multiple sclerosis,Alzheimer's disease,and amyotrophic lateral sclerosis,all of which involve oligodendroglial and myelin dysfunction.

关键词： animal models demyelination fish mammals multiple sclerosis myelin neurodegeneration oligodendrocytes oligodendroglial lineage remyelination

A Spatial Cognitive Model that Integrates the Effects of Endogenous and Exogenous Information on the Hippocampus and Striatum

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2021年第4期18卷 632-644页

作者： Jing Huang He-Yuan Yang Xiao-Gang Ruan Nai-Gong Yu Guo-Yu Zuo Hao-Meng Liu Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational intelligence and intelligence system Beijing 100124China

Reproducing the spatial cognition of animals using computational models that make agents navigate autonomously has attracted much attention. Many biologically inspired models for spatial cognition focus mainly on the simulation of the hippocampus and only consider the effect of external environmental information(i.e., exogenous information) on the hippocampal coding. However, neurophysiological studies have shown that the striatum, which is closely related to the hippocampus, also plays an important role in spatial cognition and that information inside animals(i.e., endogenous information) also affects the encoding of the hippocampus. Inspired by the progress made in neurophysiological studies, we propose a new spatial cognitive model that consists of analogies between the hippocampus and striatum. This model takes into consideration how both exogenous and endogenous information affects coding by the environment. We carried out a series of navigation experiments that simulated a water maze and compared our model with other models. Our model is self-adaptable and robust and has better performance in navigation path length. We also discuss the possible reasons for the results and how our findings may help us understand real mechanisms in the spatial cognition of animals.

关键词： Exogenous and endogenous information hippocampus striatum spatial cognition brain-inspired computation

Porn Streamer Recognition in Live Video Based on Multimodal Knowledge Distillation

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第6期30卷 1096-1102页

作者： WANG Liyuan ZHANG Jing YAO Jiacheng ZHUO Li Faculty of Information Beijing University of Technology Beijing Key Laboratory of Computational intelligence and Intelligent system Beijing University of Technology

Although deep learning has reached a higher accuracy for video content analysis, it is not satisfied with practical application demands of porn streamer recognition in live video because of multiple parameters,complex structures of deep network model. In order to improve the recognition efficiency of porn streamer in live video, a deep network model compression method based on multimodal knowledge distillation is ***, the teacher model is trained with visual-speech deep network to obtain the corresponding porn video prediction score. Second, a lightweight student model constructed with Mobile Net V2 and Xception transfers the knowledge from the teacher model by using multimodal knowledge distillation strategy. Finally, porn streamer in live video is recognized by combining the lightweight student model of visualspeech network with the bullet screen text recognition network. Experimental results demonstrate that the proposed method can effectively drop the computation cost and improve the recognition speed under the proper accuracy.

关键词： recognition speed lightweight student model computer aided instruction live video video content analysis feature extraction data compression video signal processing recognition efficiency multimodal knowledge distillation strategy deep learning bullet screen text recognition network corresponding porn video prediction score visual-speech deep network teacher model learning (artificial intelligence) deep network model compression method user modelling porn streamer recognition

Deep Scalogram Representations for Acoustic Scene Classification

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2018年第3期5卷 662-669页

作者： Zhao Ren Kun Qian Zixing Zhang Vedhas Pandit Alice Baird Bjorn Schuller ZD.B Chair of Embedded intelligence for Health Care and Wellbeing University of Augsburg Germany Machine intelligence and Signal Processing group Technische Universitat Munchen group on Language Audio and Music (GLAM) Imperial College London UK IEEE

Spectrogram representations of acoustic scenes have achieved competitive performance for acoustic scene classification. Yet, the spectrogram alone does not take into account a substantial amount of time-frequency information. In this study, we present an approach for exploring the benefits of deep scalogram representations, extracted in segments from an audio stream. The approach presented firstly transforms the segmented acoustic scenes into bump and morse scalograms, as well as spectrograms; secondly, the spectrograms or scalograms are sent into pre-trained convolutional neural networks; thirdly,the features extracted from a subsequent fully connected layer are fed into(bidirectional) gated recurrent neural networks, which are followed by a single highway layer and a softmax layer;finally, predictions from these three systems are fused by a margin sampling value strategy. We then evaluate the proposed approach using the acoustic scene classification data set of 2017 IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events(DCASE). On the evaluation set, an accuracy of 64.0 % from bidirectional gated recurrent neural networks is obtained when fusing the spectrogram and the bump scalogram, which is an improvement on the 61.0 % baseline result provided by the DCASE 2017 organisers. This result shows that extracted bump scalograms are capable of improving the classification accuracy,when fusing with a spectrogram-based system.

关键词： Acoustic scene classification(ASC) (bidirectional) gated recurrent neural networks((B) GRNNs) convolutional neural networks(CNNs) deep scalogram representation spectrogram representation

Towards a Service-Oriented Architecture for a Mobile Assistive system with Real-time Environmental Sensing

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2016年第6期21卷 581-597页

作者： Darpan Triboan Liming Chen Feng Chen Zumin Wang the Context Intelligence and Interaction Research Group (CIIRG) De Montfort University the Department of Information Engineering Dalian University

With the growing aging population, age-related diseases have increased considerably over the *** response to these, Ambient Assistive Living（AAL） systems are being developed and are continually evolving to enrich and support independent living. While most researchers investigate robust Activity Recognition（AR）techniques, this paper focuses on some of the architectural challenges of the AAL systems. This work proposes a system architecture that fuses varying software design patterns and integrates readily available hardware devices to create Wireless Sensor Networks（WSNs） for real-time applications. The system architecture brings together the Service-Oriented Architecture（SOA）, semantic web technologies, and other methods to address some of the shortcomings of the preceding system implementations using off-the-shelf and open source components. In order to validate the proposed architecture, a prototype is developed and tested positively to recognize basic user activities in real time. The system provides a base that can be further extended in many areas of AAL systems,including composite AR.

关键词： Activities of Daily Living (ADL) Service-Oriented Architecture (SOA) semantic web ontology modeling Web Ontology Language (OWL) Activity Recognition (AR) Smart Homes (SH) Wireless Sensor Networks (WSNs)

MDKB-Bot:A Practical Framework for Multi-Domain Task-Oriented Dialogue system

在线全文

学校读者我要写书评

暂无评论

Data intelligence 2019年第2期1卷 176-186页

作者： Yadi Lao Weijie Liu Sheng Gao Si Li Pattern Recognition and intelligence system Laboratory Beijing University of Posts and TelecommunicationsBeijing 100876China

One of the major challenges to build a task-oriented dialogue system is that dialogue state transition frequently happens between multiple domains such as booking hotels or ***,the encoder-decoder model based on the end-to-end neural network has become an attractive approach to meet this ***,it usually requires a sufficiently large amount of training data and it is not flexible to handle dialogue state *** paper addresses these problems by proposing a simple but practical framework called Multi-Domain KB-BOT(MDKB-BOT),which leverages both neural networks and rule-based strategy in natural language understanding(NLU)and dialogue management(DM).Experiments on the data set of the Chinese Human-Computer Dialogue Technology Evaluation Campaign show that MDKB-BOT achieves competitive performance on several evaluation metrics,including task completion rate and user satisfaction.

关键词： Dialogue system Knowledge base Natural language understanding Slot filling Natural language generation

Improving performance of robots using human-inspired approaches: a survey

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第12期65卷 5-35页

作者： Hong QIAO Shanlin ZHONG Ziyu CHEN Hongze WANG State Key Laboratory of Management and Control for Complex system Institute of Automation Chinese Academy of Sciences School of Artifcial intelligence University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and intelligence Technology

Realizing high performance of ordinary robots is one of the core problems in robotic research. Improving the performance of ordinary robots usually relies on the collaborative development of multiple research fields, resulting in high costs and difficulty to complete some high-precision tasks. As a comparison,humans can realize extraordinary overall performance under the condition of limited computational-energy consumption and low absolute precision in sensing and controlling each body unit. Therefore, developing human-inspired robotic systems and algorithms is a promising avenue to improve the performance of robotic systems. In this review, the cutting-edge research work on human-inspired intelligent robots in decisionmaking, cognition, motion control, and system design is summarized from behavior-and neural-inspired aspects. This review aims to provide a significant insight into human-inspired intelligent robots, which may be beneficial for promoting the integration of neuroscience, machinery, and control, so as to develop a new generation of robotic systems.

关键词： human-inspired intelligent robots brain-inspired intelligence decision making visual cognition musculoskeletal robots

Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1797-1809页

作者： Ding Wang Jiangyu Wang Mingming Zhao Peng Xin Junfei Qiao IEEE Faculty of Information Technology the Beijing Key Laboratory of Computational Intelligence and Intelligent Systemthe Beijing Laboratory of Smart Environmental Protectionand the Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China

This paper is concerned with a novel integrated multi-step heuristic dynamic programming(MsHDP)algorithm for solving optimal control *** is shown that,initialized by the zero cost function,MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman(HJB)***,the stability of the system is analyzed using control policies generated by ***,a general stability criterion is designed to determine the admissibility of the current control *** is,the criterion is applicable not only to traditional value iteration and policy iteration but also to ***,based on the convergence and the stability criterion,the integrated MsHDP algorithm using immature control policies is developed to accelerate learning efficiency ***,actor-critic is utilized to implement the integrated MsHDP scheme,where neural networks are used to evaluate and improve the iterative policy as the parameter ***,two simulation examples are given to demonstrate that the learning effectiveness of the integrated MsHDP scheme surpasses those of other fixed or integrated methods.

关键词： Adaptive critic artificial neural networks Hamilton-Jacobi-Bellman(HJB)equation multi-step heuristic dynamic programming multi-step reinforcement learning optimal control