发布求助
文献互助 智能选刊 最新文献

2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)最新文献

筛选
英文 中文
On the Cognitive Foundations of Autonomous Systems and General AI 论自治系统和通用人工智能的认知基础
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811328
Yingxu Wang
{"title":"On the Cognitive Foundations of Autonomous Systems and General AI","authors":"Yingxu Wang","doi":"10.1109/ICCICC53683.2021.9811328","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811328","url":null,"abstract":"It is recognized that autonomous systems are advanced intelligent systems towards general AI that may think and infer. This work investigates into basic research on the cognitive foundations of autonomous systems. Key challenges to real-time intelligence generation are analyzed in classic stored-programmed-controlled computing and data-regressed ion AI, which lead to a general intelligence generation methodology of knowledge-inferred AI. A theoretical framework of autonomous AI systems is elaborated towards autonomous systems for enabling deep machine thinking, knowledge learning, cognitive computing, and mission-critical intelligent systems.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115428206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
An Agent-Based Model for Evolution of Cooperation With Proactive Information Gathering 基于agent的主动信息收集合作演化模型
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.24124/2018/58875
Nahid Mohammad Taheri, J. Polajnar, Liang Chen
{"title":"An Agent-Based Model for Evolution of Cooperation With Proactive Information Gathering","authors":"Nahid Mohammad Taheri, J. Polajnar, Liang Chen","doi":"10.24124/2018/58875","DOIUrl":"https://doi.org/10.24124/2018/58875","url":null,"abstract":"This paper explores a new model to investigate the impact of proactive information gathering upon the evolution of cooperation among self-interested agents in a multiagent system. It builds upon an existing game-theoretical model of spatially distributed mobile agent population with the energy-based individual life cycle. Respective agents keep playing one-shot Prisoner’s Dilemma games in neighbourhood encounters. Agents in the new model can dynamically adjust their strategies towards different types of opponents. Simulation experiments are carried out on establishing patterns of how this ability impacts the evolution of cooperation in the presence of varying levels of environmental adversity. The results show that cooperation prevails in a substantially larger area of parameter space than in the basic model without information gathering.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130224359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Synchrony-Based State Representation for Classification by Liquid State Machines 基于同步的液态机分类状态表示
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811304
Nicolas Pajot, M. Boukadoum
{"title":"Synchrony-Based State Representation for Classification by Liquid State Machines","authors":"Nicolas Pajot, M. Boukadoum","doi":"10.1109/ICCICC53683.2021.9811304","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811304","url":null,"abstract":"The Liquid State Machine (LSM) models usually ignore the influence of the liquid state representation on performance, with the assumption that the latter depends only on the readout circuit. The typical decoding of the liquid’s spike trains is achieved with spike rate-based vectors that are input into the readout circuit. This occults the spike timing, a central aspect of biological neural coding, with potentially detrimental consequences on performance. We propose a model of liquid state representation that builds the feature vectors from the temporal information about the spike trains, hence using spike synchrony instead of rate. Using Poisson-distributed spike trains in noisy conditions, we show that such model outperforms a rate-only model in distinguishing spike train pairs, regardless of the frequency chosen to sample the liquid state or the noise level. In the same vein, we suggest a synchrony-based measure of the Separation Property (SP), a core feature of LSMs regarding classification performance, for a more robust and biologically plausible interpretation.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121392394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
FERNIE-ViL: Facial Expression Enhanced Vision-and-Language Model 面部表情增强视觉和语言模型
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811331
Soo-Ryeon Lee, Dohyun Kim, Mingyu Lee, SangKeun Lee
{"title":"FERNIE-ViL: Facial Expression Enhanced Vision-and-Language Model","authors":"Soo-Ryeon Lee, Dohyun Kim, Mingyu Lee, SangKeun Lee","doi":"10.1109/ICCICC53683.2021.9811331","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811331","url":null,"abstract":"Visual cognition requires analyzing actions, intentions, and emotions of persons in a given image. Visual Commonsense Reasoning (VCR) is a task that selects rationales and answers to questions for given images. In VCR, facial expressions are important nonverbal signals because they convey emotions and intentions in human interactions. However, ERNIE-ViL and UNITER, which are vision-and-language models to get image and text representations, do not learn them. We find that ERNIE-ViL and UNITER are vulnerable to the problem of identifying emotions. In this paper, therefore, we propose facial expression recognition FERNIE-ViL, which adapts a facial expression recognition module to the existing vision-and-language model. Experimental results (2.4% point improvement on VCR Q→A and 0.3% point improvement on VCR QA→R) demonstrate that our method can enhance visual commonsense reasoning by understanding human interactions.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126195981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Dynamic neural network approach to human emotion: an analysis based on sliding time windows 人类情感的动态神经网络方法:基于滑动时间窗的分析
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811310
Jingqiu Wang, Gen Shi, N. Ma, Yang Sun, Xia Li, J. Sui
{"title":"Dynamic neural network approach to human emotion: an analysis based on sliding time windows","authors":"Jingqiu Wang, Gen Shi, N. Ma, Yang Sun, Xia Li, J. Sui","doi":"10.1109/ICCICC53683.2021.9811310","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811310","url":null,"abstract":"Emotion is a key motivational factor of a person strivings for health and well-being. Understanding neural networks supporting different types of emotion bears far-reaching implications for mental health. Recent studies suggest that emotional processing is associated with a large number of brain regions. However, the precise functional connectivity (FC) of these regions in investigations of emotional processing are largely unknown. To address this issue, we recruited 359 participants who completed emotional-related measures including the Positive and Negative Affect Schedule (PANAS) the Self-Compassion Scale, while scanned with resting-state functional magnetic resonance images (fMRI). Here, we proposed a novel psychological characteristics analysis framework by using a dynamic sliding window method to characterize the nature of resting-state functional connectivity in the human brain, in relation to the static FC method. The comparison results showed that the dynamic FC method produced the better performance, compared to the static FC method. The global network analyses across all 6 possible connectivity matrices further demonstrated that the dynamically hemispheric asymmetry best predicted emotional processing. The dynamic FC method was evaluated on the three emotional labels - positive emotion, negative emotion, self-compassion and the best prediction performance was consistently observed in the dynamically hemispheric asymmetric FC.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116099708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research on traffic accident fatality prediction based on BP neural network 基于BP神经网络的交通事故死亡预测研究
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811306
Hong Liu, Xiaobin Xiong, Yan Jiang, Zihui Guan, Lijuan Liu
{"title":"Research on traffic accident fatality prediction based on BP neural network","authors":"Hong Liu, Xiaobin Xiong, Yan Jiang, Zihui Guan, Lijuan Liu","doi":"10.1109/ICCICC53683.2021.9811306","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811306","url":null,"abstract":"Through the analysis of the influencing factors and correlation of traffic accidents, the main indexes affecting the death toll of traffic accidents are GDP, population, number of motor vehicle drivers, highway mileage, highway passenger turnover, highway freight volume and highway freight turnover. GM (1,1) and BP neural network are used to fit and train the traffic accident death toll from 1998 to 2017 respectively. The average error of GM (1,1) fitting and BP neural network training is 9.22% and 1.95% respectively, which shows that the training effect of BP neural network is better than that of GM (1,1). Using GM (1, 1) and BP neural network model to predict the number of traffic accident fatalities in 2018-2019 respectively, GM (1, 1) predicts that the number of traffic accident deaths from 2018 to 2019 is 52000 and 47000 and BP neural network predicts that the number of traffic accident deaths from 2018 to 2019 are both 60000. The average error of GM (1,1) and BP neural network prediction is 21.4% and 4.8%, respectively, indicating that the prediction result of BP neural network is more accurate. The prediction method and results provide reference for the management of transportation departments, and realize the transformation from traffic accidents to prevention.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114085077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Safety risk evaluation of coal mine based on average weighted combination weight 基于平均加权组合权的煤矿安全风险评价
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811315
Xueyan Zhang, Zhuhua Hu, H. Liu, Cheng Huang
{"title":"Safety risk evaluation of coal mine based on average weighted combination weight","authors":"Xueyan Zhang, Zhuhua Hu, H. Liu, Cheng Huang","doi":"10.1109/ICCICC53683.2021.9811315","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811315","url":null,"abstract":"In order to comprehensively, accurately and quantitatively evaluate coal mine safety conditions, various factors affecting mine safety production have been comprehensively considered from the four aspects of man, machine, environment, and management, and a coal mine safety risk evaluation index system has been constructed. Using the analytic hierarchy process, entropy method, and coefficient of variation method to determine the index weights, and using the weighted average method to obtain the combined weights of the index system, fully integrate the weight information of the above three weighting methods, and avoid the influence of subjective scoring by experts. The coal mine risk value is calculated by the fuzzy comprehensive evaluation method, and the safety status is divided into 4 grades in the \"Coal Mine Safety Regulations\", and the mine risk grade of 2# and 3# coal mines is evaluated to be at level IV (unsafe), 1#, 4 #The coal mine risk level is at level III (less safe).","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124428075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research on YOLOv4-tiny traffic sign detection algorithm with attention mechanism 基于注意机制的yolov4微型交通标志检测算法研究
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811295
Yu Gong, Jun Peng, Shangzhu Jin, Xiaobing Li, Yuchun Tan
{"title":"Research on YOLOv4-tiny traffic sign detection algorithm with attention mechanism","authors":"Yu Gong, Jun Peng, Shangzhu Jin, Xiaobing Li, Yuchun Tan","doi":"10.1109/ICCICC53683.2021.9811295","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811295","url":null,"abstract":"In the process of traffic sign detection, the small and dense traffic signs which are influenced by bad weather, similar interference and other natural environment, lead to poor detection performance. To solve these problems, this paper proposes a target detection network based on improved YOLOv4-tiny, which improves the original YOLOv4-tiny backbone extraction network through the attention mechanism based on channel, and obtains a new backbone extraction network to increase the interpretability of neural network. K-means clustering algorithm is used to calculate the anchor value which is suitable for the experimental dataset. The experiment results show that, compared with the original model, the mAP value of the improved model is increased by 1.81% and our model can effectively improve the performance of small target detection. It only needs 0.8s to get the traffic sign detection results, which can meet the real-time requirements of practical application scenarios.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128016331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A General Theory of Adaptivity and Homeostasis in the Brain and in the Body 大脑和身体的适应性和内稳态的一般理论
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/iccicc53683.2021.9811329
B. Widrow
{"title":"A General Theory of Adaptivity and Homeostasis in the Brain and in the Body","authors":"B. Widrow","doi":"10.1109/iccicc53683.2021.9811329","DOIUrl":"https://doi.org/10.1109/iccicc53683.2021.9811329","url":null,"abstract":"Hebbian learning is widely accepted in the fields of psychology, neurology, and neurobiology. It is one of the fundamental premises of neuroscience. The LMS (least mean square) algorithm of Widrow and Hoff is the world’s most widely used adaptive algorithm, fundamental in the fields of signal processing, control systems, communication systems, pattern recognition, and artificial neural networks. These learning paradigms are very different. Hebbian learning is unsupervised. LMS learning is supervised. However, a form of LMS can be constructed to perform unsupervised learning and, as such, LMS can be used in a natural way to implement Hebbian learning. Combining the two paradigms creates a new unsupervised learning algorithm, Hebbian-LMS. This algorithm has practical engineering applications and provides insight into learning in living neural networks. A fundamental question is, how does learning take place in living neural networks? \"Nature’s little secret,\" the learning algorithm practiced by nature at the neuron and synapse level, may well be the Hebbian-LMS algorithm.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129447983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Representation of the Problem-Solving Process of the Tower of Hanoi using Fuzzy Cognitive Maps 用模糊认知地图表征河内塔的问题解决过程
2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2021-10-29 DOI: 10.1109/ICCICC53683.2021.9811321
Adán A. Gómez, Laura A. Márquez
{"title":"Representation of the Problem-Solving Process of the Tower of Hanoi using Fuzzy Cognitive Maps","authors":"Adán A. Gómez, Laura A. Márquez","doi":"10.1109/ICCICC53683.2021.9811321","DOIUrl":"https://doi.org/10.1109/ICCICC53683.2021.9811321","url":null,"abstract":"Fuzzy cognitive maps represent the knowledge system of both an individual and a group, wherein the data collected from study participants are used to develop quantitative dynamic models from qualitative static models. The objective of this paper was to construct a dynamic representation model of the Tower of Hanoi problem using fuzzy cognitive maps. The methodology of this paper included five main phases: application of the Stroop test, warm-up, the experiment itself, data analysis, and creating a representation of the Tower of Hanoi problem-solving process. The results obtained show that fuzzy cognitive maps allow the researchers to identify the degree of influence between specific verbal instructions and their causal relationship concerning the categories of executive processes and subprocesses developed by the participants. It is necessary to continue deepening this research to design future studies that identify new functions at the cognitive and metacognitive levels in these specific problem-solving contexts.","PeriodicalId":101653,"journal":{"name":"2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131544138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信