2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)最新文献_第6页

Boosting Few-Shot Image Recognition Via Domain Alignment Prototypical Networks 基于域对齐原型网络的少量图像识别

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00048

Jiang Lu, Zhong Cao, Kailun Wu, Gang Zhang, Changshui Zhang

{"title":"Boosting Few-Shot Image Recognition Via Domain Alignment Prototypical Networks","authors":"Jiang Lu, Zhong Cao, Kailun Wu, Gang Zhang, Changshui Zhang","doi":"10.1109/ICTAI.2018.00048","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00048","url":null,"abstract":"Human has the ability of drawing inferences about other things from only one instance. Few-shot learning is aimed at imitating this generalized learning behavior of human beings, where the learning machine is expected to recognize novel categories not seen in the training set, given only a few training data for each novel category. In this paper, we enhance the Prototypical Network for few-shot learning tasks by introducing a domain alignment module, which takes into account the domain shifts existing between different categories. Compared to original Prototypical Network (PN), the most excellent model for few-shot learning at present, our proposed Domain Alignment Prototypical Network (DA-PN) is able to abate the distribution differences among the data of training and test classes, further optimizing the embedding space of prototype feature for each category and then boosting few-shot recognition. Comprehensive empirical evidence demonstrates that the proposed DA-PN can yield state-of-the-art few-shot recognition performance on the public benchmark dataset mini-ImageNet as well as a novel proposed few-shot dataset MNIST&CIFAR10.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125166985","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

Building and Interpreting Risk Models from Imbalanced Clinical Data 从不平衡的临床数据中建立和解释风险模型

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00031

Aaron N. Richter, T. Khoshgoftaar

引用次数: 2

Object Detection with Neural Models, Deep Learning and Common Sense to Aid Smart Mobility 利用神经模型、深度学习和常识进行目标检测，帮助智能移动

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00134

Abidha Pandey, Manish Puri, A. Varde

{"title":"Object Detection with Neural Models, Deep Learning and Common Sense to Aid Smart Mobility","authors":"Abidha Pandey, Manish Puri, A. Varde","doi":"10.1109/ICTAI.2018.00134","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00134","url":null,"abstract":"The advent of autonomous transportation systems is attracting attention in AI today. Despite how far this area has progressed, there are situations better handled by humans. One of these is distinguishing objects seen for the first time and making decisions accordingly. Hence, our focus in this paper is on object detection, which can potentially enhance autonomous driving and other types of automation in transportation systems. This impacts Smart Mobility in Smart Cities. We provide expanded analysis of recent object detection techniques including neural models, deep learning and related advances. We highlight a novel object detection system called YOLO (You Only Look Once) and conduct its performance evaluation on real-time data. We point out challenges in this field and then explore the use of Commonsense Knowledge (CSK) in object detection with neural models and deep learning, emphasizing the importance of CSK to capture intuitive human reasoning. We explain how this work would potentially enhance autonomous vehicles and transportation systems. This work thus constitutes an exploratory paper that embodies a vision in Smart Mobility.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124452472","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: 27

Social Recommendation Based on Implicit Friends Discovering Via Meta-Path 基于元路径内隐好友发现的社交推荐

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00039

Yuqi Song, Min Gao, Junliang Yu, Qingyu Xiong

{"title":"Social Recommendation Based on Implicit Friends Discovering Via Meta-Path","authors":"Yuqi Song, Min Gao, Junliang Yu, Qingyu Xiong","doi":"10.1109/ICTAI.2018.00039","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00039","url":null,"abstract":"With the growing popularity of online social platforms, it has been universally recognized that incorporating social relations into recommender systems can usually alleviate the problem of data sparsity. However, social recommender systems based on explicit relations are not as successful as expected due to the noise and the social cold issue of explicit social links. The intuition of utilizing explicit relations is that users share similar preferences if they are friends in the social network. In fact, quite a lot of users who are distant from each other in the social network also have similar tastes. The user item network and the user social network can provide useful information that can complement each other, so that exploring the implicit friends using the heterogeneous network they formed would be more helpful. In this paper, we propose an approach IFSR to discover implicit friends over the heterogeneous network to improve the performance of social recommendation. To find out reliable implicit ties, we first model the system as a heterogeneous network upon which both the preferences and social information are coupled. Over the HIN, similarities between each pair of users can be quantified through network embedding based representation learning. To reduce the computational cost while preserving the information embedded in the original networks and uncover the latent information hiding in the HIN, several meaningful meta-paths over the HIN are designed to guide the process of random walks. Finally, the Top-K implicit friends are incorporated into a social bayesian ranking model to enhance the performance of item ranking. Experimental results on three datasets demonstrate IFSR outperforms the state-of-the-art methods and illustrate why the implicit friends are advantageous for social recommendation.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"75 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123216388","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: 4

A Stock-Movement Aware Approach for Discovering Investors' Personalized Preferences in Stock Markets 股票市场中投资者个性化偏好的股票运动感知方法

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00051

Jun Chang, Wenting Tu

引用次数: 3

Adaptive Give-Up Decisions for a Team of Robots Foraging with Task Partitioning 任务划分下机器人觅食团队的自适应放弃决策

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00075

J. Nogales, G. Oliveira

{"title":"Adaptive Give-Up Decisions for a Team of Robots Foraging with Task Partitioning","authors":"J. Nogales, G. Oliveira","doi":"10.1109/ICTAI.2018.00075","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00075","url":null,"abstract":"This work considers a team of robots foraging in a dynamic environment. The arena is divided into source and nest regions. Robots must transport objects from a source to a nest having two ways to complete this task: partitioning and non-partitioning. When partitioning, a robot carries the object until an area for transference while another robot may pick it up later to carry it to a nest. The non-partitioning option uses an alternative path that allows robots traveling back and forth between the regions. Robot decisions are based on experienced time to complete the transportation. Robots look for the faster option. We proposed two decision-making models: M-SGU (model for Static give up function) and M-AGU (model for adaptive give up function). M-AGU allows adaptation while robots forage and delivered the most promising results. We changed the delay to transfer an object to reproduce dynamic conditions that could be faced in real environments. Due to these changeable conditions, robots have to consider whether to abandon or struggle to complete the current task. The proposed decision-making strategies use a new adaptive give up function to make robots decide considering costs on both options and mixing old and new information. Simulation results show that robots reach faster adaptations leading to more objects successfully transported when using the proposed M-AGU strategy, which is also scalable to larger teams.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121116067","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

Online Single Homogeneous Source Transfer Learning Based on AdaBoost 基于AdaBoost的在线单同质源迁移学习

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00061

Chen Qian, Heng-yang Lu, Chong-Jun Wang

{"title":"Online Single Homogeneous Source Transfer Learning Based on AdaBoost","authors":"Chen Qian, Heng-yang Lu, Chong-Jun Wang","doi":"10.1109/ICTAI.2018.00061","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00061","url":null,"abstract":"Transfer learning has made great achievements in many fields and many excellent algorithms have been proposed. In recent years, many scholars have focused on a new research area called online transfer learning, which is different from general transfer learning. Online transfer learning concentrates on how to build a good classifier on the target domain when the training data arrive in an online/sequential manner. This paper focuses on online transfer learning problem based on a single source domain under homogeneous space. The existing algorithms HomOTL-I and HomOTL-II simply ensemble the classifiers on the source and target domains directly. When the distribution difference between the source domain and the target domain is large, it will not result in a good transfer effect. We are inspired by the idea of the boosting algorithm, that is we could form a strong classification model by a combination of multiple weak classifications. We train multiple classifiers on the source domain in an offline manner using AdaBoost algorithm, combine these classifiers on source domain with the classifier trained in an online manner on the target domain to form multiple weak combination in an ensemble manner. Based on the above ideas, we propose two algorithms AB-HomOTL-I and AB-HomOTLII, which have different ways to adjust the weights. We tested our algorithms on sentiment analysis dataset and 20newsgroup dataset. The results show that our algorithms are superior to other baseline algorithms","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132744051","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: 4

Plan and Goal Recognition as HTN Planning 计划和目标识别作为HTN计划

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00078

D. Höller, P. Bercher, G. Behnke, Susanne Biundo-Stephan

引用次数: 34

An Improved Laplacian Semi-Supervised Regression 一种改进的拉普拉斯半监督回归

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00092

V. Kraus, Seif-Eddine Benkabou, K. Benabdeslem, F. Cherqui

引用次数: 1

A General Framework for Querying Possibilistic RDF Data 查询可能性RDF数据的通用框架

2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI) Pub Date : 2018-11-01 DOI: 10.1109/ICTAI.2018.00033

Amna Abidi, Mohamed Anis Bach Tobji, A. Hadjali, B. B. Yaghlane

引用次数: 3