检索结果-内蒙古大学图书馆

Evolvable dialogue state tracking for statistical dialogue management

Frontiers of computer science 2016年第2期10卷 201-215页

作者： Kai YU Lu CHEN Kai SUN Qizhe XIE Su ZHU Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive EngineeringSpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China Department of Computer Science Cornell University Ithaca NY 14853 USA

Statistical dialogue management is the core of cognitive spoken dialogue systems （SDS） and has attracted great research interest. In recent years, SDS with the ability of evolution is of particular interest and becomes the cuttingedge of SDS research. Dialogue state tracking （DST） is a process to estimate the distribution of the dialogue states at each dialogue turn, given the previous interaction history. It plays an important role in statistical dialogue management. To provide a common testbed for advancing the research of DST, international DST challenges （DSTC） have been organised and well-attended by major SDS groups in the world. This paper reviews recent progresses on rule-based and statistical approaches during the challenges. In particular, this paper is focused on evolvable DST approaches for dialogue domain extension. The two primary aspects for evolution, semantic parsing and tracker, are discussed. Semantic enhancement and a DST framework which bridges rule-based and statistical models are introduced in detail. By effectively incorporating prior knowledge of dialogue state transition and the ability of being data-driven, the new framework supports reliable domain extension with little data and can continuously improve with more data available. This makes it excellent candidate for DST evolution. Experiments show that the evolvable DST approaches can achieve the state-of-the-art performance and outperform all previously submitted trackers in the third DSTC.

关键词： dialogue management domain extension,evolvable dialogue state tracking parser tracker

来源：评论

学校读者我要写书评

暂无评论

IMPROVING WORLD MODELS USING DEEP SUPERVISION WITH LINEAR PROBES

arXiv

引用

arXiv 2025年

作者： Zahorodnii, Andrii Department of Electrical Engineering and Computer Science MIT United States Department of Brain and Cognitive Sciences McGovern Institute for Brain Research MIT CambridgeMA United States

Developing effective world models is crucial for creating artificial agents that can reason about and navigate complex environments. In this paper, we investigate a deep supervision technique for encouraging the development of a world model in a network trained end-to-end to predict the next observation. While deep supervision has been widely applied for task-specific learning, our focus is on improving the world models. Using an experimental environment based on the Flappy Bird game, where the agent receives only LIDAR measurements as observations, we explore the effect of adding a linear probe component to the network’s loss function. This additional term encourages the network to encode a subset of the true underlying world features into its hidden state. Our experiments demonstrate that this supervision technique improves both training and test performance, enhances training stability, and results in more easily decodable world features – even for those world features which were not included in the training. Furthermore, we observe a reduced distribution drift in networks trained with the linear probe, particularly during high-variability phases of the game (flying between successive pipe encounters). Including the world features loss component roughly corresponded to doubling the model size, suggesting that the linear probe technique is particularly beneficial in compute-limited settings or when aiming to achieve the best performance with smaller models. These findings contribute to our understanding of how to develop more robust and sophisticated world models in artificial agents, paving the way for further advancements in this field. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A computational evaluation of gender asymmetry in semantic change 43

A computational evaluation of gender asymmetry in semantic c...

引用

43rd Annual Meeting of the cognitive science Society: Comparative Cognition: Animal Minds, CogSci 2021

作者： Schnell, Eric Xu, Yang Cognitive Science and Mathematics Programs University of Toronto Canada Department of Computer Science Cognitive Science Program University of Toronto Canada

A fundamental goal in cognitive and historical linguistic research on semantic change is to characterize the regularity in how word meanings change over time. We examine a common belief that has not yet been evaluated comprehensively, which asserts that gender of a word influences its direction of semantic change. By this account, female terms like mistress should undergo pejorative change in meaning systematically more so than male terms like master. We evaluate this claim in gender-marked word pairs in English and French respectively as languages without and with grammatical gender. Our results provide supporting evidence for gender asymmetry in semantic change of English words but not French words. Our study raises questions about the generality of the claim about gender asymmetry in semantic change and provides a scalable computational framework for understanding the social roots of word meaning change. © cognitive science Society: Comparative Cognition: Animal Minds, CogSci *** rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Monitoring blood pressure through a single hybrid hemodynamic signal with a flexible optoelectronic patch

Device

引用

Device 2025年

作者： Zhong, Yizhou Zhang, Yongcao Pu, Jing Wustoni, Shofarul Uribe, Johana Lopez-Larrea, Naroa Marks, Adam McCulloch, Iain Mecerreyes, David Baran, Derya Inal, Sahika Organic Bioelectronics Laboratory Biological and Environmental Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Materials Science and Engineering Program (MSE) Physical Sciences and Engineering Division (PSE) KAUST Thuwal 23955-6900 Saudi Arabia POLYMAT University of the Basque Country UPV/EHU Avenida Tolosa 72 Guipuzcoa Donostia-San Sebastian 20018 Spain Department of Chemistry University of Oxford Oxford OX1 3TF United Kingdom Andlinger Center for Energy and the Environment and Department of Electrical and Computer Engineering Princeton University Princeton 08544 NJ United States IKERBASQUE Basque Foundation for Science Plaza Euskadi 5 Bilbao 48009 Spain

Hemodynamics, the study of blood flow and circulatory forces, is fundamental for assessing cardiovascular health, disease states, and therapeutic outcomes. Here, we introduce a skin-conformable organic optoelectronic thin-film patch (ePatch) designed to simultaneously capture electrocardiography (ECG) and photoplethysmography (PPG) signals as a single hybrid signal, named the electrocardio-photoplethysmogram (EC-PPG). The ePatch integrates an organic electrochemical transistor (OECT), an organic photodiode, surface-mounted light-emitting diodes, and electrochemical electrodes on a flexible, skin-conforming substrate. By training deep learning models on the hybrid EC-PPG data, we achieved accurate arterial blood pressure estimations, with mean errors of just 1.69 mmHg for systolic and 0.89 mmHg for diastolic blood pressure, outperforming traditional predictions that rely on individual physiological signals as inputs. Our findings underscore the potential of EC-PPG as a compound hemodynamic signal for AI-driven vital sign monitoring and integrated, solution-processable soft electronics for clinical and point-of-care applications. © 2025 The Authors

关键词： DTI-3: Develop electrocardiography electrophysiology flexible electronics OECT OPD organic electrochemical transistor photoplethysmography wearable electronics

来源：评论

学校读者我要写书评

暂无评论

Coalition Formation for Heterogeneous Federated Learning Enabled Channel Estimation in RIS-assisted Cell-free MIMO

arXiv

引用

arXiv 2025年

作者： Qi, Nan Liu, Haoxuan Tsiftsis, Theodoros A. Boulogeorgos, Alexandros-Apostolos A. Zhou, Fuhui Jin, Shi Wu, Qihui Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China Department of Informatics and Telecommunications University of Thessaly Lamia35100 Greece Department of Electrical and Computer Engineering University of Western Macedonia Kozani50100 Greece National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China

Downlink channel estimation remains a significant bottleneck in reconfigurable intelligent surface-assisted cell-free multiple-input multiple-output communication systems. Conventional approaches primarily rely on centralized deep learning methods to estimate the high-dimensional and complex cascaded channels. These methods require data aggregation from all users for centralized model training, leading to excessive communication overhead and significant data privacy concerns. Additionally, the large size of local learning models imposes heavy computational demands on end users, necessitating strong computational capabilities that most commercial devices lack. To address the aforementioned challenges, a coalition-formation-guided heterogeneous federated learning (FL) framework is proposed. This framework leverages coalition formation to guide the formation of heterogeneous FL user groups for efficient channel estimation. Specifically, by utilizing a distributed deep reinforcement learning (DRL) approach, each FL user intelligently and independently decides whether to join or leave a coalition, aiming at improving channel estimation accuracy, while reducing local model size and computational costs for end users. Moreover, to accelerate the DRL-FL convergence process and reduce computational burdens on end users, a transfer learning method is introduced. This method incorporates both received reference signal power and distance similarity metrics, by considering that nodes with similar distances to the base station and comparable received signal power have a strong likelihood of experiencing similar channel fading. Massive experiments performed that reveal that, compared with the benchmarks, the proposed framework significantly reduces the computational overhead of end users by 16%, improves data privacy, and improves channel estimation accuracy by 20%. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Role of high energy photons in dual spectral source rapid isothermal CVD

引用

JOURNAL OF ELECTRONIC MATERIALS 1997年第10期26卷 1184-1188页

作者： Singh, R Chen, Y Department of Electrical and Computer Engineering Material Science and Engineering Program Clemson University Clemson Department of Electrical and Computer Engineering Clemson University Clemson

The use of tungsten halogen lamps and the deuterium lamp as the source of thermal and optical energies has been exploited to deposit thin films of Ta2O5 on Si and conducting substrates, The leakage current densities are as low as 10(-10) A/cm(2) for gate voltage under 5V. Photons in visible, ultraviolet, and vacuum ultraviolet (lambda < 800 nm) regions provide higher bulk and surface diffusion coefficients as well as reduced activation energy for the chemical process involved in the chemical vapor deposition process. The low thermal mass of the substrate provides limited reaction processing capability. The photochemical and photophysical processes allow the participating atoms and molecules to adjust their bond geometries and occupy sites which result in overall reduction of stress and strain energy and provide materials with overall low microscopic defects at low processing temperature and with high throughput. New experimental results of Al-Ta2O5-Si3N4-poly Si-Al structure are presented. The leakage current-voltage characteristics are better than those reported by other researchers.

关键词： dielectrics metalorganic chemical vapor deposition (MOCVD) rapid isothermal processing (RIP) Ta2O5

来源：评论

学校读者我要写书评

暂无评论

Large language models for diabetes training:a prospective study

引用

science Bulletin 2025年第6期70卷 934-942页

作者： Haoxuan Li Zehua Jiang Zhouyu Guan Yuqian Bao Yuexing Liu Tingting Hu Jiajia Li Ruhan Liu Liang Wu Di Cheng Hongwei Ji Yong Wang Ya-Xing Wang Carol Y.Cheung Yingfeng Zheng Jihong Wang Zhen Li Weibing Wu Cynthia Ciwei Lim Yong Mong Bee Hong Chang Tan Elif I.Ekinci David C.Klonoff Justin B.Echouffo-Tcheugui Nestoras Mathioudakis Leonor Corsino Rafael Simó Charumathi Sabanayagam Gavin Siew Wei Tan Ching-Yu Cheng Tien Yin Wong Huating Li Chun Cai Lijuan Mao Lee-Ling Lim Yih-Chung Tham Bin Sheng Weiping Jia Shanghai University of Sport Shanghai 200438China School of Clinical Medicine Beijing Tsinghua Changgung HospitalTsinghua MedicineTsinghua UniversityBeijing 100084China Beijing Visual Science and Translational Eye Research Institute(BERI) Tsinghua MedicineTsinghua UniversityBeijing 100084China Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and EngineeringSchool of ElectronicInformationand Electrical EngineeringShanghai Jiao Tong UniversityDepartment of Endocrinology and MetabolismShanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of MedicineShanghai Diabetes InstituteShanghai Clinical Center for DiabetesShanghai 200240China MoE Key Lab of Artificial Intelligence Artificial Intelligence InstituteShanghai Jiao Tong UniversityShanghai 200240China Department of Cardiology the Affiliated Hospital of Qingdao UniversityQingdao 266011China CEMS NCMISHCMSMADISAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematics University of Chinese Academy of SciencesChinese Academy of SciencesBeijing 100049China Key Laboratory of Systems Health Science of Zhejiang Province School of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China Beijing Institute of Ophthalmology Beijing Tongren HospitalCapital Medical UniversityBeijing Ophthalmology and Visual Sciences Key LaboratoryBeijing 100730China k.Department of Ophthalmology and Visual Sciences The Chinese University of Hong KongHong Kong 999077China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic CenterSun Yat-sen UniversityGuangdong Provincial Key Laboratory of Ophthalmology and Visual ScienceGuangdong Provincial Clinical Research Center for Ocular DiseasesGuangzhou 510060China Department of Renal Medicine Singapore General HospitalSingHealth-Duke Academic Medical CentreSingapore169

Diabetes poses a considerable global health challenge,with varying levels of diabetes knowledge among healthcare professionals,highlighting the importance of diabetes *** Language Models(LLMs)provide new insights into diabetes training,but their performance in diabetes-related queries remains uncertain,especially outside the English language like *** first evaluated the performance of ten LLMs:ChatGPT-3.5,ChatGPT-4.0,Google Bard,LlaMA-7B,LlaMA2-7B,Baidu ERNIE Bot,Ali Tongyi Qianwen,MedGPT,HuatuoGPT,and Chinese LlaMA2-7B on diabetes-related queries,based on the Chinese National Certificate Examination for Primary Diabetes Care in China(NCE-CPDC)and the English Specialty Certificate Examination in Endocrinology and Diabetes of Membership of the Royal College of Physicians of the United ***,we assessed the training of primary care physicians(PCPs)without and with the assistance of ChatGPT-4.0 in the NCE-CPDC examination to ascertain the reliability of LLMs as medical *** found that ChatGPT-4.0 outperformed other LLMs in the English examination,achieving a passing accuracy of 62.50%,which was significantly higher than that of Google Bard,LlaMA-7B,and *** the NCE-CPFC examination,ChatGPT-4.0,Ali Tongyi Qianwen,Baidu ERNIE Bot,Google Bard,MedGPT,and ChatGPT-3.5 successfully passed,whereas LlaMA2-7B,HuatuoGPT,Chinese LLaMA2-7B,and LlaMA-7B ***-4.0(84.82%)surpassed all PCPs and assisted most PCPs in the NCE-CPDC examination(improving by 1%–6.13%).In summary,LLMs demonstrated outstanding competence for diabetes-related questions in both the Chinese and English language,and hold great potential to assist future diabetes training for physicians globally.

关键词： Diabetes Diabetestraining Largelanguagemodels Primarydiabetescare Prospectivestudy

来源：评论

学校读者我要写书评

暂无评论

TextAI 3.0 (Multimodal): multimodal sentiment analysis using attention-enabled ensemble-based deep learning in hyperbolic space

引用

International Journal of Information Technology (Singapore) 2025年 1-16页

作者： Singh, Jaskaran Sanga, Prabhav Khanna, Narendra N. Laird, John R. Singh, Inder M. Kalra, Mannudeep K. Mantella, Laura E. Johri, Amer M. Faa, Gavino Tiwari, Ekta Singh, Rajesh Abbas, Mohamed Saba, Luca Suri, Jasjit S. Stroke Monitoring and Diagnostic Division AtheroPoint™ Roseville 95661 CA United States Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Cardiology Indraprastha APOLLO Hospitals New Delhi 110001 India Department of Neurology and Stroke Program University of Maryland School of Medicine Baltimore United States Department of Radiology Harvard Medical School Boston 02115 MA United States Department of Biomedical and Molecular Sciences Queen’s University Kingston ON Canada Division of Cardiology Department of Medicine Queen’s University Kingston ON Canada Department of Pathology University of Cagliari Cagliari Italy Department of Computer Science Visvesvaraya National Institute of Technology (VNIT) Nagpur 440010 India Department of Research and Innovation Uttaranchal Institute of Technology Uttaranchal University Dehradun 248007 India Central Labs King Khalid University P.O. Box 960 AlQura’a Abha Saudi Arabia Electrical Engineering Department College of Engineering King Khalid University Abha 61421 Saudi Arabia Department of Neurology University of Cagliari Cagliari Italy Department of ECE Idaho State University Pocatello 83209 ID United States Department of CE Graphic Era Deemed to Be University Dehradun 248002 India University Center for Research and Development Chandigarh University Mohali India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Campus Pune India Department of Innovation Global Biomedical Technologies Inc. Roseville 95661 CA United States

The rising prevalence of depression presents a significant global health challenge, underscoring the need for effective early detection through sentiment analysis. Traditional multimodal sentiment analysis methods, which rely on Euclidean space for data representation, often fail to capture the complex hierarchical relationships and non-linear structures inherent in multimodal data. To address this limitation, we propose a novel multimodal architecture that operates in hyperbolic space and incorporates attention-based ensemble learning to enhance feature representation and model performance. We developed and evaluated ten AI models—five utilizing Euclidean space and five leveraging hyperbolic space—on the Spoken Language Understanding Evaluation (SLUE) benchmark dataset. The models were assessed using cross-validation techniques to ensure robustness, and statistical analyses were conducted to validate the findings. Our results indicate that hyperbolic-based multimodal models achieve a 2.32% improvement in accuracy compared to their Euclidean counterparts, while the integration of self-attention mechanisms further contributes an average accuracy gain of 0.96%. Additionally, we observed a 3.76% decline in performance when reducing the training-to-test data ratio from 90:10 to 50:50, highlighting the importance of data distribution in model training. These findings confirm that attention-enhanced multimodal models in hyperbolic space offer superior representations for sentiment analysis. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Attention-enabled Deep learning Euclidean space Hyperbolic space Multimodal Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

The GLAIR cognitive architecture

引用

International Journal of Machine Consciousness 2010年第2期2卷 307-332页

作者： Shapiro, Stuart C. Bona, Jonathan P. Department of Computer Science and Engineering Center for Cognitive Science State University of New York at Buffalo Buffalo NY 14260-2000 United States

GLAIR (Grounded Layered Architecture with Integrated Reasoning) is a multilayered cognitive architecture for embodied agents operating in real, virtual, or simulated environments containing other agents. The highest layer of the GLAIR Architecture, the Knowledge Layer (KL), contains the beliefs of the agent, and is the layer in which conscious reasoning, planning, and act selection is performed. The lowest layer of the GLAIR Architecture, the Sensori-Actuator Layer (SAL), contains the controllers of the sensors and effectors of the hardware or software robot. Between the KL and the SAL is the Perceptuo-Motor Layer (PML), which grounds the KL symbols in perceptual structures and subconscious actions, contains various registers for providing the agent's sense of situatedness in the environment, and handles translation and communication between the KL and the SAL. The motivation for the development of GLAIR has been "Computational Philosophy", the computational understanding and implementation of human-level intelligent behavior without necessarily being bound by the actual implementation of the human mind. Nevertheless, the approach has been inspired by human psychology and biology. © 2010 World Scientific Publishing Company.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

TODIM and TOPSIS with Z-numbers

引用

Frontiers of Information Technology & Electronic engineering 2019年第2期20卷 283-291页

作者： Renato A.KROHLING André G.C.PACHECO Guilherme A.dos SANTOS Department of Production Engineering Federal University of Espirito Santo Graduate Program in Computer Science Federal University of Espirito Santo

In this paper, we present an approach that can handle Z-numbers in the context of multi-criteria decision-making problems. The concept of Z-number as an ordered pair Z=(A, B) of fuzzy numbers A and B is used, where A is a linguistic value of a variable of interest and B is a linguistic value of the probability measure of A. As human beings, we communicate with each other by means of natural language using sentences like "the journey from home to university most likely takes about half an hour." The Z-numbers are converted to fuzzy numbers. Then the Z-TODIM and Z-TOPSIS are presented as a direct extension of the fuzzy TODIM and fuzzy TOPSIS, respectively. The proposed methods are applied to two case studies and compared with the standard approach using crisp values. The results obtained show the feasibility of the approach.

关键词： Multi-criteria decision-making TODIM TOPSIS Fuzzy number Z-number

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：