Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence最新文献

How to Promote Group Performance?: From the Perspective of Event Characteristics 如何提升团队表现?:从事件特征的角度

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377729

Jun Qian, Xiao Sun, Y. Chai, Yi Liu

引用次数: 0

DOS-SLAM: A Real-time Dynamic Object Segmentation Visual SLAM System DOS-SLAM:一个实时动态目标分割视觉SLAM系统

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377731

He Xu, Sheng Zhang, Pengyu Liu

引用次数: 2

Extracting Word Embeddings via Joint Learning of Syntagmatic and Paradigmatic Structure 基于组合结构和聚合结构联合学习的词嵌入提取

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377803

Chao Wei, Lijun Zhu, Juncheng Wang, Jiaoxiang Shi, Z. Wang, Liang Chen

{"title":"Extracting Word Embeddings via Joint Learning of Syntagmatic and Paradigmatic Structure","authors":"Chao Wei, Lijun Zhu, Juncheng Wang, Jiaoxiang Shi, Z. Wang, Liang Chen","doi":"10.1145/3377713.3377803","DOIUrl":"https://doi.org/10.1145/3377713.3377803","url":null,"abstract":"In this work, we explore the latent distributional semantic between each given word and its context in a way of reconstruction, and propose an Auto-encoder architecture to encourage the model pay attention to the interactions of Syntagmatic and Paradigmatic structure of context (SPC). In particular, SPC represent the syntagmatic words of the context through a vocabulary co-occurrence matrix, and extract a likely embedding for a better joint predicting of all paradigmatic words to fill in the input context. During the error back propagation, our model focus on the salient statistical structure by allowing a sub-network to approximate the nonzero sub-matrix. Finally, we trained our model on a public Wikipedia corpus and evaluated on word analogy, word similarity tasks and documents clustering and classification. The results show that our method yields almost 4% improvement on word analogy and nearly 3% improvement on word similarity tasks compared to state-of-the-art methods. The evidences demonstrate that SPC outperform baseline and the state-of-the-art methods on all tasks.","PeriodicalId":357409,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115330825","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

A Template Based Approach for Training NMT for Low-Resource Uralic Languages - A Pilot with Finnish 基于模板的乌拉尔语言NMT培训方法——芬兰语试点

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377801

Mika Hämäläinen, Khalid Alnajjar

引用次数: 17

A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting ARIMA、LSTM和GRU在时间序列预测中的比较

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377722

Peter T. Yamak, Li Yujian, P. K. Gadosey

引用次数: 135

Research on Intelligent Video Surveillance System in Remote Area Based on NB-IoT 基于NB-IoT的远程智能视频监控系统研究

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377750

Rong Che, Lianqing Wang, Yinchuan Wang, Q. Lin

引用次数: 3

Designing Intelligent Personalized Chatbot for Hotel Services 面向酒店服务的智能个性化聊天机器人设计

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377791

F. P. Putri, H. Meidia, D. Gunawan

{"title":"Designing Intelligent Personalized Chatbot for Hotel Services","authors":"F. P. Putri, H. Meidia, D. Gunawan","doi":"10.1145/3377713.3377791","DOIUrl":"https://doi.org/10.1145/3377713.3377791","url":null,"abstract":"Development of chatbot in customer services and sales are remarkable. However, there is only little research in developing chatbot-hotel in Indonesia. Chatbot has many advantages for both hotel and mobile users to improve convenience, reduce service, sales and support costs, one-to-one marketing and new data collections. Using chatbot, customers using smartphone can reach a hotel anytime and anywhere with personalized services related to their needs. The customers can find out availability of rooms, price, booking and have a personal front office that provide the real-time and context-relevant information about hotel services. Therefore, we develop an interactive intelligent personalized chatbot-hotel by using AIML and Google Flutter. Flutter is used as it is easy to develop the chatbot-hotel in the cross-platform mobile application. The outcome of this work is a prototype chatbot-hotel on mobile platform especially for Indonesian users. This chatbot includes all services in the hotels and able to give the personalized services to the customers before arrive in the hotel. It can accommodate the customer needs and to up-selling the hotel facilities.","PeriodicalId":357409,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114646433","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

Evolutionary NetArchitecture Search for Deep Neural Networks Pruning 深度神经网络剪枝的进化网络结构搜索

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377739

Shuxin Chen, Lin Lin, Zixun Zhang, M. Gen

{"title":"Evolutionary NetArchitecture Search for Deep Neural Networks Pruning","authors":"Shuxin Chen, Lin Lin, Zixun Zhang, M. Gen","doi":"10.1145/3377713.3377739","DOIUrl":"https://doi.org/10.1145/3377713.3377739","url":null,"abstract":"Network pruning is an architecture search process to determine the state (remove/remain) of neurons in the network. It is a com- binatorial optimization problem, and this combinatorial optimiza- tion problem is NP-hard. Most existing pruning methods prune channels/neurons based on the assumption that they are indepen- dent in network. However, there exists dependency among chan- nels/neurons. We try to solve the combinatorial optimization problem by evolutionary algorithm (EA). However, the traditional EA can't be used directly into deep neural networks (DNNs) because the problem dimension is too high. Attention mechanism (AM) can help us get parameter important score to reduce prob- lem difficulty, making the architecture search process more effective. Therefore, combining EA and AM, we propose an Evolutionary NetArchitecture Search (EvoNAS) method to solve network pruning problem. We demonstrate the effectiveness of our method on common datasets with ResNet, ResNeXt, and VGG. For example, for ResNet on CIFAR-10, EvoNAS reduces 73.40% computing operations and 73.95% parameters with 0.13% test accuracy increasement. Compared with the state-of-the-art methods, EvoNAS increases 30% reduction ratio at least.","PeriodicalId":357409,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124015052","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: 8

Arabic Twitter Corpus for Crisis Response Messages Classification 阿拉伯语Twitter语料库危机响应信息分类

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377799

Ghadah Adel, Yuping Wang

{"title":"Arabic Twitter Corpus for Crisis Response Messages Classification","authors":"Ghadah Adel, Yuping Wang","doi":"10.1145/3377713.3377799","DOIUrl":"https://doi.org/10.1145/3377713.3377799","url":null,"abstract":"Twitter has been used intensively by Arab users after the crisis caused by the \"Arab Spring\". Humanity crisis in countries such as Yemen and Syria led people to utilize Twitter as a crisis communication tool to overcome uncertainty. A variety of crisis-related messages is sent to enquire about different issues. The content of these messages is used by humanitarian organizations to form the response plan. However, most of these messages are in the Arabic language that covers information about the humanitarian crisis. Classifying their content relay on annotated corpus. Though, most of the crisis corpora available are in the English language and focusing on natural hazards. In this paper, we present the first humanity crisis corpus in the Arabic language using Twitter data which annotated data into five-crisis categories. Then, classification was performed through three different experiments using TFIDF, lexical, morphology and word embedding features. After that supervised learning algorithms were trained with and without word2vec models. Results indicate that classifiers are detecting more Arabic crisis-message classes when they are trained with skip-gram with TFIDF, lexical and morphology extracted features. Moreover, we generated Arabic crisis word embedding with similarity weighting trained by word2vec techniques in each crisis category. This paper is a baseline for Arabic crisis-message classification in social media and opens up prospects for future inspiring ideas in this field.","PeriodicalId":357409,"journal":{"name":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129723950","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

Study of Mammography Medical Imaging Sample Selection Based on CSAL 基于CSAL的乳腺摄影医学影像样本选择研究

Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2019-12-20 DOI: 10.1145/3377713.3377795

Jiyun Li, Wenlong Mi

引用次数: 0