2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)最新文献_第2页

EEG Signals Feature Extraction and Artificial Neural Networks Classification for The Diagnosis of Schizophrenia 脑电信号特征提取及人工神经网络分类在精神分裂症诊断中的应用

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450257

Lei Zhang

引用次数: 3

Intelligent Mathematics (IM): Indispensable Mathematical Means for General AI, Autonomous Systems, Deep Knowledge Learning, Cognitive Robots, and Intelligence Science 智能数学:通用人工智能、自主系统、深度知识学习、认知机器人和智能科学不可或缺的数学手段

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450252

Yingxu Wang

{"title":"Intelligent Mathematics (IM): Indispensable Mathematical Means for General AI, Autonomous Systems, Deep Knowledge Learning, Cognitive Robots, and Intelligence Science","authors":"Yingxu Wang","doi":"10.1109/ICCICC50026.2020.9450252","DOIUrl":"https://doi.org/10.1109/ICCICC50026.2020.9450252","url":null,"abstract":"It is recognized that the core knowledge of humans in natural sciences and engineering is archived in mathematical forms. Intelligent Mathematics (IM) is a category of contemporary denotational mathematics extending classic analytic mathematics as defined in real numbers (R). IM represents a collection of novel mathematical structures that formalizes rigorous expressions and manipulations on complex entities known as hyperstructures (H) beyond R. Instances of the complex entities in H include formal concepts, semantics, relations, knowledge, intelligence, behavioral processes, causality, inferences, and systems. Paradigms of IM developed in my lab include real-time process algebra (RTPA), concept algebra, semantic algebra, system algebra, inference algebra, fuzzy probability algebra, big data algebra, image frame algebra, and the causal probability theory, etc.This keynote speech presents the IM foundations of emerging intelligent science and AI paradigms. A set of novel IMs will be presented for rigorously manipulating complex cognitive entities in the brain and abstract intelligence including data, information, knowledge, and intelligence from the bottom up. IM will lead to the emergence of mathematical engineering (ME), which addresses the challenges in formal structural and functional modeling of complex mental objects and their rigorous manipulations in a wide range of applications such as cognitive robots, autonomous systems, intelligent IoT, and unmanned systems.","PeriodicalId":212248,"journal":{"name":"2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116851465","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: 6

Improvement of Data Fusion with Threading Technology in Home UbiHealth 基于线程技术的家庭健康数据融合改进

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450268

J. Sarivougioukas, Aristides Th. Vagelatos

{"title":"Improvement of Data Fusion with Threading Technology in Home UbiHealth","authors":"J. Sarivougioukas, Aristides Th. Vagelatos","doi":"10.1109/ICCICC50026.2020.9450268","DOIUrl":"https://doi.org/10.1109/ICCICC50026.2020.9450268","url":null,"abstract":"According to the ubiquitous computing paradigm, dispersed computers within the home environment can support the residents’ health by being aware of all the developing and evolving situations. The context-awareness of the supporting computers stems from the data acquisition of the occurring events at home. In some cases, different sensors provide input of identical type, thereby raising conflict-related issues. Thus, for each type of input data, fusion methods must be applied on the raw data to obtain a dominant input value. Also, for diagnostic inference purpose, data fusion methods must be applied on the values of the available classes of multiple contextual data structures. Dempster-Shafer theory offers the algorithmic tools to efficiently fuse the data of each input type or class. However, the fusion manipulations of large data volumes within strict time limits impose significant computational overhead. In the present work, threading technology is employed to take advantage of the processing capabilities of modern computers for the data fusion of the contextual parameter sensor readings, along with the selection of appropriate computing architectures and matching algorithms. The advantages offered by the proposed approach are presented and analyzed.","PeriodicalId":212248,"journal":{"name":"2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116058246","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

Local Learning in Point Clouds based on Spectral Pooling 基于谱池的点云局部学习

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450222

Yushi Li, G. Baciu

{"title":"Local Learning in Point Clouds based on Spectral Pooling","authors":"Yushi Li, G. Baciu","doi":"10.1109/ICCICC50026.2020.9450222","DOIUrl":"https://doi.org/10.1109/ICCICC50026.2020.9450222","url":null,"abstract":"As one of the most fundamental geometric data types for the representation of space and object shapes, a point cloud usually maintains much structural information about the spatial relationship between objects and their features. However, the relative sparseness of point clouds sampled in most practical applications make extracting information-rich features a major challenge. Traditionally, feature extraction algorithms resorted to structured feature engineering and used handcrafted representations for some specific problems. Motivated by the development of deep neural networks, many researchers started to handle the unstructured point clouds from the raw data samples of 3D scanning devices. Some important advantages that deep learning frameworks have over traditional feature engineering is generalizing complex features and associated semantic concepts in a hierarchical manner. Deep learning models have achieved significant landmarks in cognitive processing of speech, image, and video signals. However, unlike in 2D image processing, a 3D point cloud is irregular and sparse. Hence, traditional network frameworks are difficult to apply on 3D geometric data directly. In this paper, we propose to integrate a local point convolution network with spectral pooling to aggregate and learn features in 3D point clouds. The benefits of our framework are fast convergence and competitive performance on point cloud classification.","PeriodicalId":212248,"journal":{"name":"2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133901722","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

Misspelling Correction with Pre-trained Contextual Language Model 用预训练的语境语言模型校正拼写错误

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450253

Yifei Hu, X. Jing, Youlim Ko, Julia Taylor Rayz

{"title":"Misspelling Correction with Pre-trained Contextual Language Model","authors":"Yifei Hu, X. Jing, Youlim Ko, Julia Taylor Rayz","doi":"10.1109/ICCICC50026.2020.9450253","DOIUrl":"https://doi.org/10.1109/ICCICC50026.2020.9450253","url":null,"abstract":"Spelling irregularities, known now as spelling mistakes, have been found for several centuries. As humans, we are able to understand most of the misspelled words based on their location in the sentence, perceived pronunciation, and context. Unlike humans, computer systems do not possess the convenient auto complete functionality of which human brains are capable. While many programs provide spelling correction functionality, many systems do not take context into account. Moreover, Artificial Intelligence systems function in the way they are trained on. With many current Natural Language Processing (NLP) systems trained on grammatically correct text data, many are vulnerable against adversarial examples, yet correctly spelled text processing is crucial for learning. In this paper, we investigate how spelling errors can be corrected in context, with a pre-trained language model BERT. We present two experiments, based on BERT and the edit distance algorithm, for ranking and selecting candidate corrections. The results of our experiments demonstrated that when combined properly, contextual word embeddings of BERT and edit distance are capable of effectively correcting spelling errors.","PeriodicalId":212248,"journal":{"name":"2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134478009","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: 13

Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference 自然语言推断的纯假设模型中词汇不规则性的探索

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450263

Qingyuan Hu, Yi Zhang, Kanishka Misra, J. Rayz

{"title":"Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference","authors":"Qingyuan Hu, Yi Zhang, Kanishka Misra, J. Rayz","doi":"10.1109/ICCICC50026.2020.9450263","DOIUrl":"https://doi.org/10.1109/ICCICC50026.2020.9450263","url":null,"abstract":"Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) is the task of predicting the entailment relation between a pair of sentences (premise and hypothesis). This task has been described as “a valuable testing ground for the development of semantic representations” [1], and is a key component in natural language understanding evaluation benchmarks. Models that understand entailment should encode both, the premise and the hypothesis. However, experiments by Poliak et al. [2] revealed a strong preference of these models towards patterns observed only in the hypothesis, based on a 10 dataset comparison. Their results indicated the existence of statistical irregularities present in the hypothesis that bias the model into performing competitively with the state of the art. While recast datasets provide large scale generation of NLI instances due to minimal human intervention, the papers that generate them do not provide fine-grained analysis of the potential statistical patterns that can bias NLI models. In this work, we analyze hypothesis-only models trained on one of the recast datasets provided in Poliak et al. [2] for word-level patterns. Our results indicate the existence of potential lexical biases that could contribute to inflating the models’ performance.","PeriodicalId":212248,"journal":{"name":"2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127483966","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

Predicting the Retweet Level of COVID-19 Tweets with Neural Network Classifier 用神经网络分类器预测COVID-19推文的转发水平

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450271

Z. Qu, Z. Ding

引用次数: 1

An Empirical Study of Underlying Cognitive Factors in Complex Problem-Solving Collaboration 复杂问题解决协作中潜在认知因素的实证研究

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450274

Yingting Chen, T. Kanno, K. Furuta

引用次数: 2

[ICCI*CC 2020 Front cover] [ICCI*CC 2020封面]

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/iccicc50026.2020.9450273

引用次数: 0

A Hybrid Brain-Inspired Computing Architecture towards Artificial General Intelligence 面向人工通用智能的混合脑启发计算架构

2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2020-09-26 DOI: 10.1109/ICCICC50026.2020.9450260

Luping Shi

引用次数: 0