Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems最新文献

UBAL UBAL

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372443

Kristína Malinovská, L. Malinovský, Pavel Kršek, Svatopluk Kraus, I. Farkaš

{"title":"UBAL","authors":"Kristína Malinovská, L. Malinovský, Pavel Kršek, Svatopluk Kraus, I. Farkaš","doi":"10.1145/3372422.3372443","DOIUrl":"https://doi.org/10.1145/3372422.3372443","url":null,"abstract":"Artificial neural networks, in particular the deep end-to-end architectures trained by error backpropagation (BP), are currently the topmost used learning systems. However, learning in such systems is only loosely inspired by the actual neural mechanisms. Algorithms based on local activation differences were designed as a biologically plausible alternative to BP. We propose Universal Bidirectional Activation-based Learning, a novel neural model derived from contrastive Hebbian learning. Similarly to what is assumed about learning in the brain, our model defines a single learning rule that can perform multiple ways of learning via special hyperparameters. Unlike others, our model consists of mutually dependent, yet separate weight matrices for different directions of activation propagation. We show that UBAL can learn different tasks (such as pattern retrieval, denoising, or classification) with different setups of the learning hyperparameters. We also demonstrate the performance of our algorithm on a machine learning benchmark (MNIST). The experimental results presented in this paper confirm that UBAL is comparable with a basic version BP-trained multilayer network and the related biologically-motivated models.","PeriodicalId":118684,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115372823","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 Method of Pedestrian Trajectory Prediction Based on LSTM 基于LSTM的行人轨迹预测方法

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372428

Xuefeng Jiang, Wei Lin, Junrui Liu

引用次数: 3

Representation Learning by Convolutional Neural Network for Smartphone Sensor Based Activity Recognition 基于卷积神经网络表征学习的智能手机传感器活动识别

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372439

Tatsuhito Hasegawa, M. Koshino

{"title":"Representation Learning by Convolutional Neural Network for Smartphone Sensor Based Activity Recognition","authors":"Tatsuhito Hasegawa, M. Koshino","doi":"10.1145/3372422.3372439","DOIUrl":"https://doi.org/10.1145/3372422.3372439","url":null,"abstract":"Although many researchers have widely investigated activity recognition using smartphone sensing, estimation accuracy can be adversely affected by individual dependence. The result of our survey showed that the process of smartphone sensor based activity recognition that has not been sufficiently discussed, especially using representation learning by Convolutional Neural Network (CNN). The effectiveness of the representation learning model using CNN in activity recognition was verified, as were 10 types of activity recognition models: Deep Neural Network (DNN) using Hand-Crafted (HC) features, simple CNN model, AlexNet, SE-AlexNet, Fully Convolutional Network (FCN), SE-FCN, VGG, SE-VGG, ResNet, and SE-ResNet, using a benchmark dataset for human activity recognition. Finally, the deep learning models were trained a total of 600 times (10 models, 6 types with varying the number of people in training dataset, and 10 trials to reduce the influence of randomness bias). The results indicate that SE-VGG is the most accurate, as many subjects can be comprised in the training data.","PeriodicalId":118684,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129624709","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

Deep Learning Based-Recommendation System: An Overview on Models, Datasets, Evaluation Metrics, and Future Trends 基于深度学习的推荐系统:模型、数据集、评估指标和未来趋势概述

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372444

Kyle Ong, S. Haw, K. Ng

引用次数: 7

Analysis Instrument of Smart Technology Capability for an Industry: a Total Smart Technology Capability Perspective 产业智能技术能力分析工具:一个整体智能技术能力视角

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372426

C. Yoon

引用次数: 0

Transformer based Chinese Sentiment Classification 基于变压器的汉语情感分类

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372438

Zhengshuai Zhu, Yanquan Zhou, Shuhao Xu

引用次数: 3

A System for Cultivating Exploration Skills by Presenting Clues Based on the Analysis of Page Selection Behaviors 基于页面选择行为分析的线索探究技能培养体系

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372449

Yota Kawawa, R. Onuma, H. Nakayama, H. Kaminaga, Y. Miyadera, Shoichi Nakamura

{"title":"A System for Cultivating Exploration Skills by Presenting Clues Based on the Analysis of Page Selection Behaviors","authors":"Yota Kawawa, R. Onuma, H. Nakayama, H. Kaminaga, Y. Miyadera, Shoichi Nakamura","doi":"10.1145/3372422.3372449","DOIUrl":"https://doi.org/10.1145/3372422.3372449","url":null,"abstract":"Activities performed on the Web have becoming increasingly more complicated. In such activities, the importance of Web exploration through trial and error has increased. To satisfactorily conduct such exploration, it is important for users to comprehend the process of Web exploration and reflect on their search intentions when constructing queries. However, such tasks are difficult for inexperienced people. In this research, we focus on searchers' behaviors of page selection in the Web exploration process. On the basis of behavior analysis, we have developed methods to extract the clues so that unskilled searchers can become aware of the evaluation against pages they acquired and utilize them in further searches. We develop a novel mechanism for cultivating exploration skills by presenting clues in accordance with a searcher's degree of Web exploration experience. In this paper, we describe the design of a support system based on our methods and the characteristics of our prototype with some snapshots.","PeriodicalId":118684,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128037355","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: 1

Finger Recognition Using a Wearable Device while Typing 在打字时使用可穿戴设备进行手指识别

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372440

Daisuke Hamazaki, Tatsuhito Hasegawa

引用次数: 1

A Constructive Multilevel Security System with Cryptographic Techniques by using Cyber-Physical System in the Space/Defense Applications 空间/国防应用中基于信息物理系统的密码技术构建多级安全系统

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372427

S. C. V. Bhaskar, Jagadam Vijay Gopal, S. Anitha

引用次数: 1

Performance Evaluation of XML Query Processing in Centralized and Distributed Environment 集中与分布式环境下XML查询处理的性能评价

Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems Pub Date : 2019-11-23 DOI: 10.1145/3372422.3372431

S. Subramaniam, S. Haw, Lay-Ki Soon

引用次数: 1